diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanContextSparkJob.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanContextSparkJob.java
index 55fdbac59a..10a3d44650 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanContextSparkJob.java
+++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanContextSparkJob.java
@@ -47,8 +47,8 @@ public class CleanContextSparkJob implements Serializable {
 		String inputPath = parser.get("inputPath");
 		log.info("inputPath: {}", inputPath);
 
-		String workingPath = parser.get("workingPath");
-		log.info("workingPath: {}", workingPath);
+		String workingDir = parser.get("workingDir");
+		log.info("workingDir: {}", workingDir);
 
 		String contextId = parser.get("contextId");
 		log.info("contextId: {}", contextId);
@@ -67,12 +67,12 @@ public class CleanContextSparkJob implements Serializable {
 			isSparkSessionManaged,
 			spark -> {
 
-				cleanContext(spark, contextId, verifyParam, inputPath, entityClazz, workingPath);
+				cleanContext(spark, contextId, verifyParam, inputPath, entityClazz, workingDir);
 			});
 	}
 
 	private static <T extends Result> void cleanContext(SparkSession spark, String contextId, String verifyParam,
-		String inputPath, Class<T> entityClazz, String workingPath) {
+		String inputPath, Class<T> entityClazz, String workingDir) {
 		Dataset<T> res = spark
 			.read()
 			.textFile(inputPath)
@@ -106,11 +106,11 @@ public class CleanContextSparkJob implements Serializable {
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
-			.json(workingPath);
+			.json(workingDir);
 
 		spark
 			.read()
-			.textFile(workingPath)
+			.textFile(workingDir)
 			.map(
 				(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz),
 				Encoders.bean(entityClazz))
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJob.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJob.java
index d35dbc7c18..b4678cc6c6 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJob.java
+++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJob.java
@@ -3,8 +3,11 @@ package eu.dnetlib.dhp.oa.graph.clean.cfhb;
 
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
+import java.util.Iterator;
+import java.util.List;
 import java.util.Objects;
 import java.util.Optional;
+import java.util.stream.Collectors;
 import java.util.stream.Stream;
 
 import org.apache.commons.io.IOUtils;
@@ -12,8 +15,10 @@ import org.apache.commons.lang3.StringUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.FlatMapFunction;
 import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.api.java.function.MapGroupsFunction;
 import org.apache.spark.sql.*;
 import org.apache.spark.sql.expressions.Aggregator;
+import org.jetbrains.annotations.NotNull;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
@@ -52,14 +57,14 @@ public class CleanCfHbSparkJob {
 		String inputPath = parser.get("inputPath");
 		log.info("inputPath: {}", inputPath);
 
-		String workingPath = parser.get("workingPath");
-		log.info("workingPath: {}", workingPath);
+		String resolvedPath = parser.get("resolvedPath");
+		log.info("resolvedPath: {}", resolvedPath);
 
 		String outputPath = parser.get("outputPath");
 		log.info("outputPath: {}", outputPath);
 
-		String masterDuplicatePath = parser.get("masterDuplicatePath");
-		log.info("masterDuplicatePath: {}", masterDuplicatePath);
+		String dsMasterDuplicatePath = parser.get("datasourceMasterDuplicate");
+		log.info("datasourceMasterDuplicate: {}", dsMasterDuplicatePath);
 
 		String graphTableClassName = parser.get("graphTableClassName");
 		log.info("graphTableClassName: {}", graphTableClassName);
@@ -72,12 +77,12 @@ public class CleanCfHbSparkJob {
 			isSparkSessionManaged,
 			spark -> {
 				cleanCfHb(
-					spark, inputPath, entityClazz, workingPath, masterDuplicatePath, outputPath);
+					spark, inputPath, entityClazz, resolvedPath, dsMasterDuplicatePath, outputPath);
 			});
 	}
 
 	private static <T extends Result> void cleanCfHb(SparkSession spark, String inputPath, Class<T> entityClazz,
-		String workingPath, String masterDuplicatePath, String outputPath) {
+		String resolvedPath, String masterDuplicatePath, String outputPath) {
 
 		// read the master-duplicate tuples
 		Dataset<MasterDuplicate> md = spark
@@ -85,116 +90,94 @@ public class CleanCfHbSparkJob {
 			.textFile(masterDuplicatePath)
 			.map(as(MasterDuplicate.class), Encoders.bean(MasterDuplicate.class));
 
-		// read the result table
-		Dataset<T> res = spark
-			.read()
-			.textFile(inputPath)
-			.map(as(entityClazz), Encoders.bean(entityClazz));
-
 		// prepare the resolved CF|HB references with the corresponding EMPTY master ID
-		Dataset<IdCfHbMapping> resolved = res
-			.flatMap(
-				(FlatMapFunction<T, IdCfHbMapping>) r -> Stream
-					.concat(
-						r.getCollectedfrom().stream().map(KeyValue::getKey),
-						Stream
+		Dataset<IdCfHbMapping> resolved = spark
+				.read()
+				.textFile(inputPath)
+				.map(as(entityClazz), Encoders.bean(entityClazz))
+				.flatMap(
+				(FlatMapFunction<T, IdCfHbMapping>) r -> {
+					final List<IdCfHbMapping> list = Stream
 							.concat(
-								r.getInstance().stream().map(Instance::getHostedby).map(KeyValue::getKey),
-								r.getInstance().stream().map(Instance::getCollectedfrom).map(KeyValue::getKey)))
-					.distinct()
-					.map(s -> asIdCfHbMapping(r.getId(), s))
-					.iterator(),
+									r.getCollectedfrom().stream().map(KeyValue::getKey),
+									Stream
+											.concat(
+													r.getInstance().stream().map(Instance::getHostedby).map(KeyValue::getKey),
+													r.getInstance().stream().map(Instance::getCollectedfrom).map(KeyValue::getKey)))
+							.distinct()
+							.map(s -> asIdCfHbMapping(r.getId(), s))
+							.collect(Collectors.toList());
+					return list.iterator();
+				},
 				Encoders.bean(IdCfHbMapping.class));
 
-		final String resolvedPath = workingPath + "/cfHbResolved";
-
-		// set the EMPTY master ID and save it aside
+		// set the EMPTY master ID/NAME and save it
 		resolved
-			.joinWith(md, resolved.col("cfhb").equalTo(md.col("duplicate")))
+			.joinWith(md, resolved.col("cfhb").equalTo(md.col("duplicateId")))
 			.map((MapFunction<Tuple2<IdCfHbMapping, MasterDuplicate>, IdCfHbMapping>) t -> {
 				t._1().setMasterId(t._2().getMasterId());
+				t._1().setMasterName(t._2().getMasterName());
 				return t._1();
 			}, Encoders.bean(IdCfHbMapping.class))
 			.write()
 			.mode(SaveMode.Overwrite)
-			.parquet(resolvedPath);
+			.json(resolvedPath);
 
 		// read again the resolved CF|HB mapping
 		Dataset<IdCfHbMapping> resolvedDS = spark
 			.read()
-			.load(resolvedPath)
-			.as(Encoders.bean(IdCfHbMapping.class));
+			.textFile(resolvedPath)
+			.map(as(IdCfHbMapping.class), Encoders.bean(IdCfHbMapping.class));
+
+		// read the result table
+		Dataset<T> res = spark
+				.read()
+				.textFile(inputPath)
+				.map(as(entityClazz), Encoders.bean(entityClazz));
 
 		// Join the results with the resolved CF|HB mapping, apply the mapping and save it
 		res
-			.joinWith(resolvedDS, res.col("id").equalTo(resolved.col("resultId")), "left")
+			.joinWith(resolvedDS, res.col("id").equalTo(resolvedDS.col("resultId")), "left")
 			.groupByKey((MapFunction<Tuple2<T, IdCfHbMapping>, String>) t -> t._1().getId(), Encoders.STRING())
-			.agg(new IdCfHbMappingAggregator(entityClazz).toColumn())
+			.mapGroups(getMapGroupsFunction(), Encoders.bean(entityClazz))
+			//.agg(new IdCfHbMappingAggregator(entityClazz).toColumn())
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
 			.json(outputPath);
 	}
 
-	public static class IdCfHbMappingAggregator<T extends Result> extends Aggregator<IdCfHbMapping, T, T> {
+	@NotNull
+	private static <T extends Result> MapGroupsFunction<String, Tuple2<T, IdCfHbMapping>, T> getMapGroupsFunction() {
+		return new MapGroupsFunction<String, Tuple2<T, IdCfHbMapping>, T>() {
+			@Override
+			public T call(String key, Iterator<Tuple2<T, IdCfHbMapping>> values) throws Exception {
+				final Tuple2<T, IdCfHbMapping> first = values.next();
+				final T res = first._1();
 
-		private final Class<T> entityClazz;
-
-		public IdCfHbMappingAggregator(Class<T> entityClazz) {
-			this.entityClazz = entityClazz;
-		}
-
-		@Override
-		public T zero() {
-			try {
-				return entityClazz.newInstance();
-			} catch (InstantiationException | IllegalAccessException e) {
-				throw new RuntimeException(e);
+				updateResult(res, first._2());
+				values.forEachRemaining(t -> updateResult(res, t._2()));
+				return res;
 			}
-		}
 
-		@Override
-		public T reduce(T r, IdCfHbMapping a) {
-			if (Objects.isNull(a) && StringUtils.isBlank(a.getMasterId())) {
-				return r;
+			private void updateResult(T res, IdCfHbMapping m) {
+				if (Objects.nonNull(m)) {
+					res.getCollectedfrom().forEach(kv -> updateKeyValue(kv, m));
+					res.getInstance().forEach(i -> {
+						updateKeyValue(i.getHostedby(), m);
+						updateKeyValue(i.getCollectedfrom(), m);
+					});
+				}
 			}
-			r.getCollectedfrom().forEach(kv -> updateKeyValue(kv, a));
-			r.getInstance().forEach(i -> {
-				updateKeyValue(i.getHostedby(), a);
-				updateKeyValue(i.getCollectedfrom(), a);
-			});
-			return r;
-		}
 
-		@Override
-		public T merge(T b1, T b2) {
-			if (Objects.isNull(b1.getId())) {
-				return b2;
+			private void updateKeyValue(final KeyValue kv, final IdCfHbMapping a) {
+				if (kv.getKey().equals(a.getCfhb())) {
+					kv.setKey(a.getMasterId());
+					kv.setValue(a.getMasterName());
+				}
 			}
-			return b1;
-		}
 
-		@Override
-		public T finish(T r) {
-			return r;
-		}
-
-		private void updateKeyValue(final KeyValue kv, final IdCfHbMapping a) {
-			if (kv.getKey().equals(a.getCfhb())) {
-				kv.setKey(a.getMasterId());
-				kv.setValue(a.getMasterName());
-			}
-		}
-
-		@Override
-		public Encoder<T> bufferEncoder() {
-			return Encoders.bean(entityClazz);
-		}
-
-		@Override
-		public Encoder<T> outputEncoder() {
-			return Encoders.bean(entityClazz);
-		}
+		};
 	}
 
 	private static IdCfHbMapping asIdCfHbMapping(String resultId, String cfHb) {
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/IdCfHbMapping.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/IdCfHbMapping.java
index cb4e1b5e62..fad1129c57 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/IdCfHbMapping.java
+++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/IdCfHbMapping.java
@@ -5,7 +5,7 @@ import java.io.Serializable;
 
 public class IdCfHbMapping implements Serializable {
 
-	private String resultid;
+	private String resultId;
 
 	private String cfhb;
 
@@ -17,15 +17,15 @@ public class IdCfHbMapping implements Serializable {
 	}
 
 	public IdCfHbMapping(String id) {
-		this.resultid = id;
+		this.resultId = id;
 	}
 
-	public String getResultid() {
-		return resultid;
+	public String getResultId() {
+		return resultId;
 	}
 
-	public void setResultid(String resultid) {
-		this.resultid = resultid;
+	public void setResultId(String resultId) {
+		this.resultId = resultId;
 	}
 
 	public String getCfhb() {
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/CleanCountrySparkJob.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/CleanCountrySparkJob.java
index 45590f789e..d8d8034586 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/CleanCountrySparkJob.java
+++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/CleanCountrySparkJob.java
@@ -58,8 +58,8 @@ public class CleanCountrySparkJob implements Serializable {
 		String inputPath = parser.get("inputPath");
 		log.info("inputPath: {}", inputPath);
 
-		String workingPath = parser.get("workingPath");
-		log.info("workingPath: {}", workingPath);
+		String workingDir = parser.get("workingDir");
+		log.info("workingDir: {}", workingDir);
 
 		String datasourcePath = parser.get("hostedBy");
 		log.info("datasourcePath: {}", datasourcePath);
@@ -85,12 +85,12 @@ public class CleanCountrySparkJob implements Serializable {
 			spark -> {
 
 				cleanCountry(
-					spark, country, verifyParam, inputPath, entityClazz, workingPath, collectedfrom, datasourcePath);
+					spark, country, verifyParam, inputPath, entityClazz, workingDir, collectedfrom, datasourcePath);
 			});
 	}
 
 	private static <T extends Result> void cleanCountry(SparkSession spark, String country, String[] verifyParam,
-		String inputPath, Class<T> entityClazz, String workingPath, String collectedfrom, String datasourcePath) {
+		String inputPath, Class<T> entityClazz, String workingDir, String collectedfrom, String datasourcePath) {
 
 		List<String> hostedBy = spark
 			.read()
@@ -134,11 +134,11 @@ public class CleanCountrySparkJob implements Serializable {
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
-			.json(workingPath);
+			.json(workingDir);
 
 		spark
 			.read()
-			.textFile(workingPath)
+			.textFile(workingDir)
 			.map(
 				(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz),
 				Encoders.bean(entityClazz))
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/GetDatasourceFromCountry.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/GetDatasourceFromCountry.java
index d3741d3e8b..598fccdd75 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/GetDatasourceFromCountry.java
+++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/country/GetDatasourceFromCountry.java
@@ -54,8 +54,8 @@ public class GetDatasourceFromCountry implements Serializable {
 		String inputPath = parser.get("inputPath");
 		log.info("inputPath: {}", inputPath);
 
-		String workingPath = parser.get("workingPath");
-		log.info("workingPath: {}", workingPath);
+		String workingPath = parser.get("workingDir");
+		log.info("workingDir: {}", workingPath);
 
 		String country = parser.get("country");
 		log.info("country: {}", country);
@@ -70,7 +70,7 @@ public class GetDatasourceFromCountry implements Serializable {
 	}
 
 	private static void getDatasourceFromCountry(SparkSession spark, String country, String inputPath,
-		String workingPath) {
+		String workingDir) {
 
 		Dataset<Organization> organization = spark
 			.read()
@@ -100,7 +100,7 @@ public class GetDatasourceFromCountry implements Serializable {
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
-			.json(workingPath);
+			.json(workingDir);
 
 	}
 }
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/clean/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/clean/oozie_app/workflow.xml
index e717fac0ff..e756840bdb 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/clean/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/clean/oozie_app/workflow.xml
@@ -343,7 +343,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/publication</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/publication</arg>
             <arg>--contextId</arg><arg>${contextId}</arg>
             <arg>--verifyParam</arg><arg>${verifyParam}</arg>
         </spark>
@@ -370,7 +370,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/dataset</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/dataset</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/dataset</arg>
             <arg>--contextId</arg><arg>${contextId}</arg>
             <arg>--verifyParam</arg><arg>${verifyParam}</arg>
         </spark>
@@ -397,7 +397,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/otherresearchproduct</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/otherresearchproduct</arg>
             <arg>--contextId</arg><arg>${contextId}</arg>
             <arg>--verifyParam</arg><arg>${verifyParam}</arg>
         </spark>
@@ -424,7 +424,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/software</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/software</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/software</arg>
             <arg>--contextId</arg><arg>${contextId}</arg>
             <arg>--verifyParam</arg><arg>${verifyParam}</arg>
         </spark>
@@ -452,7 +452,7 @@
                 --conf spark.sql.shuffle.partitions=7680
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/hostedby</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/hostedby</arg>
             <arg>--country</arg><arg>${country}</arg>
         </spark>
         <ok to="fork_clean_country"/>
@@ -485,7 +485,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/publication</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/publication</arg>
             <arg>--country</arg><arg>${country}</arg>
             <arg>--verifyParam</arg><arg>${verifyCountryParam}</arg>
             <arg>--hostedBy</arg><arg>${workingDir}/working/hostedby</arg>
@@ -514,7 +514,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/dataset</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/dataset</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/dataset</arg>
             <arg>--country</arg><arg>${country}</arg>
             <arg>--verifyParam</arg><arg>${verifyCountryParam}</arg>
             <arg>--hostedBy</arg><arg>${workingDir}/working/hostedby</arg>
@@ -543,7 +543,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/otherresearchproduct</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/otherresearchproduct</arg>
             <arg>--country</arg><arg>${country}</arg>
             <arg>--verifyParam</arg><arg>${verifyCountryParam}</arg>
             <arg>--hostedBy</arg><arg>${workingDir}/working/hostedby</arg>
@@ -572,7 +572,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/software</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
-            <arg>--workingPath</arg><arg>${workingDir}/working/software</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/working/software</arg>
             <arg>--country</arg><arg>${country}</arg>
             <arg>--verifyParam</arg><arg>${verifyCountryParam}</arg>
             <arg>--hostedBy</arg><arg>${workingDir}/working/hostedby</arg>
@@ -629,9 +629,9 @@
                 --conf spark.sql.shuffle.partitions=7680
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/publication</arg>
+            <arg>--resolvedPath</arg><arg>${workingDir}/cfHbResolved/publication</arg>
             <arg>--outputPath</arg><arg>${workingPath}/cfHbPatched/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
-            <arg>--workingDir</arg><arg>${workingDir}/working/publication</arg>
             <arg>--masterDuplicatePath</arg><arg>${workingDir}/masterduplicate</arg>
         </spark>
         <ok to="wait_clean_cfhb"/>
@@ -656,9 +656,9 @@
                 --conf spark.sql.shuffle.partitions=7680
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/dataset</arg>
+            <arg>--resolvedPath</arg><arg>${workingDir}/cfHbResolved/dataset</arg>
             <arg>--outputPath</arg><arg>${workingPath}/cfHbPatched/dataset</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
-            <arg>--workingDir</arg><arg>${workingDir}/working/dataset</arg>
             <arg>--masterDuplicatePath</arg><arg>${workingDir}/masterduplicate</arg>
         </spark>
         <ok to="wait_clean_cfhb"/>
@@ -683,9 +683,9 @@
                 --conf spark.sql.shuffle.partitions=7680
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
+            <arg>--resolvedPath</arg><arg>${workingDir}/cfHbResolved/otherresearchproduct</arg>
             <arg>--outputPath</arg><arg>${workingPath}/cfHbPatched/otherresearchproduct</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
-            <arg>--workingDir</arg><arg>${workingDir}/working/otherresearchproduct</arg>
             <arg>--masterDuplicatePath</arg><arg>${workingDir}/masterduplicate</arg>
         </spark>
         <ok to="wait_clean_cfhb"/>
@@ -710,9 +710,9 @@
                 --conf spark.sql.shuffle.partitions=7680
             </spark-opts>
             <arg>--inputPath</arg><arg>${graphOutputPath}/software</arg>
+            <arg>--resolvedPath</arg><arg>${workingDir}/cfHbResolved/software</arg>
             <arg>--outputPath</arg><arg>${workingPath}/cfHbPatched/software</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
-            <arg>--workingDir</arg><arg>${workingDir}/working/software</arg>
             <arg>--masterDuplicatePath</arg><arg>${workingDir}/masterduplicate</arg>
         </spark>
         <ok to="wait_clean_cfhb"/>
@@ -733,7 +733,7 @@
             <prepare>
                 <delete path="${graphOutputPath}/publication"/>
             </prepare>
-            <arg>${workingPath}/cfHbPatched/publication</arg>
+            <arg>${workingDir}/cfHbPatched/publication</arg>
             <arg>${graphOutputPath}/publication</arg>
         </distcp>
         <ok to="copy_wait"/>
@@ -745,7 +745,7 @@
             <prepare>
                 <delete path="${graphOutputPath}/dataset"/>
             </prepare>
-            <arg>${workingPath}/cfHbPatched/dataset</arg>
+            <arg>${workingDir}/cfHbPatched/dataset</arg>
             <arg>${graphOutputPath}/dataset</arg>
         </distcp>
         <ok to="copy_wait"/>
@@ -757,7 +757,7 @@
             <prepare>
                 <delete path="${graphOutputPath}/otherresearchproduct"/>
             </prepare>
-            <arg>${workingPath}/cfHbPatched/otherresearchproduct</arg>
+            <arg>${workingDir}/cfHbPatched/otherresearchproduct</arg>
             <arg>${graphOutputPath}/otherresearchproduct</arg>
         </distcp>
         <ok to="copy_wait"/>
@@ -769,7 +769,7 @@
             <prepare>
                 <delete path="${graphOutputPath}/software"/>
             </prepare>
-            <arg>${workingPath}/cfHbPatched/software</arg>
+            <arg>${workingDir}/cfHbPatched/software</arg>
             <arg>${graphOutputPath}/software</arg>
         </distcp>
         <ok to="copy_wait"/>
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_cfhb_parameters.json b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_cfhb_parameters.json
index 8b8a5f70e9..934d173b5b 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_cfhb_parameters.json
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_cfhb_parameters.json
@@ -11,6 +11,12 @@
     "paramDescription": "the path to the graph data dump to read",
     "paramRequired": true
   },
+  {
+    "paramName": "rp",
+    "paramLongName": "resolvedPath",
+    "paramDescription": "the path to store the resolved records",
+    "paramRequired": true
+  },
   {
     "paramName": "out",
     "paramLongName": "outputPath",
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_context_parameters.json b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_context_parameters.json
index e3d31d69f8..8be6496d8a 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_context_parameters.json
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_context_parameters.json
@@ -12,8 +12,8 @@
     "paramRequired": true
   },
   {
-    "paramName": "wp",
-    "paramLongName": "workingPath",
+    "paramName": "wd",
+    "paramLongName": "workingDir",
     "paramDescription": "the path to store the output graph",
     "paramRequired": true
   },
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json
index 318fb22f80..b38b5ac9fd 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json
@@ -12,8 +12,8 @@
     "paramRequired": true
   },
   {
-    "paramName": "wp",
-    "paramLongName": "workingPath",
+    "paramName": "wd",
+    "paramLongName": "workingDir",
     "paramDescription": "the path to store the output graph",
     "paramRequired": true
   },
diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_datasource_country_parameters.json b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_datasource_country_parameters.json
index e0aa60328d..01aa2e7b07 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_datasource_country_parameters.json
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_datasource_country_parameters.json
@@ -12,8 +12,8 @@
     "paramRequired": true
   },
   {
-    "paramName": "wp",
-    "paramLongName": "workingPath",
+    "paramName": "wd",
+    "paramLongName": "workingDir",
     "paramDescription": "the path to store the output graph",
     "paramRequired": true
   },
diff --git a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJobTest.java b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJobTest.java
new file mode 100644
index 0000000000..680d1ff64a
--- /dev/null
+++ b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/cfhb/CleanCfHbSparkJobTest.java
@@ -0,0 +1,118 @@
+package eu.dnetlib.dhp.oa.graph.clean.cfhb;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+import eu.dnetlib.dhp.schema.oaf.Dataset;
+import eu.dnetlib.dhp.schema.oaf.Publication;
+import org.apache.commons.io.FileUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+import org.junit.jupiter.api.*;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.File;
+import java.io.IOException;
+import java.net.URISyntaxException;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+
+public class CleanCfHbSparkJobTest {
+
+    private static final Logger log = LoggerFactory.getLogger(CleanCfHbSparkJobTest.class);
+
+    private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+    private static SparkSession spark;
+
+    private static Path testBaseTmpPath;
+
+    private static String resolvedPath;
+
+    private static String graphInputPath;
+
+    private static String graphOutputPath;
+
+    private static String dsMasterDuplicatePath;
+
+    @BeforeAll
+    public static void beforeAll() throws IOException, URISyntaxException {
+
+        testBaseTmpPath = Files.createTempDirectory(CleanCfHbSparkJobTest.class.getSimpleName());
+        log.info("using test base path {}", testBaseTmpPath);
+
+        final File entitiesSources = Paths
+                .get(CleanCfHbSparkJobTest.class.getResource("/eu/dnetlib/dhp/oa/graph/clean/cfhb/entities").toURI())
+                .toFile();
+
+        FileUtils
+                .copyDirectory(
+                        entitiesSources,
+                        testBaseTmpPath.resolve("input").resolve("entities").toFile());
+
+        FileUtils
+                .copyFileToDirectory(
+                        Paths
+                                .get(CleanCfHbSparkJobTest.class.getResource("/eu/dnetlib/dhp/oa/graph/clean/cfhb/masterduplicate.json").toURI())
+                                .toFile(),
+                        testBaseTmpPath.resolve("workingDir").resolve("masterduplicate").toFile());
+
+
+        graphInputPath = testBaseTmpPath.resolve("input").resolve("entities").toString();
+        resolvedPath = testBaseTmpPath.resolve("workingDir").resolve("cfHbResolved").toString();
+        graphOutputPath = testBaseTmpPath.resolve("workingDir").resolve("cfHbPatched").toString();
+        dsMasterDuplicatePath = testBaseTmpPath.resolve("workingDir").resolve("masterduplicate").toString();
+
+        SparkConf conf = new SparkConf();
+        conf.setAppName(CleanCfHbSparkJobTest.class.getSimpleName());
+
+        conf.setMaster("local[*]");
+        conf.set("spark.driver.host", "localhost");
+        conf.set("spark.ui.enabled", "false");
+
+        spark = SparkSession
+                .builder()
+                .appName(CleanCfHbSparkJobTest.class.getSimpleName())
+                .config(conf)
+                .getOrCreate();
+    }
+
+    @AfterAll
+    public static void afterAll() throws IOException {
+        FileUtils.deleteDirectory(testBaseTmpPath.toFile());
+        spark.stop();
+    }
+
+    @Test
+    void testCleanCfHbSparkJob() throws Exception {
+        final String outputPath = graphOutputPath + "/dataset";
+        CleanCfHbSparkJob
+                .main(
+                        new String[] {
+                                "--isSparkSessionManaged", Boolean.FALSE.toString(),
+                                "--inputPath", graphInputPath + "/dataset",
+                                "--outputPath", outputPath,
+                                "--resolvedPath", resolvedPath + "/dataset",
+                                "--graphTableClassName", Dataset.class.getCanonicalName(),
+                                "--datasourceMasterDuplicate", dsMasterDuplicatePath
+                        });
+
+        //final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+
+        Assertions.assertTrue(Files.exists(Paths.get(graphOutputPath, "dataset")));
+
+        final org.apache.spark.sql.Dataset<Dataset> d = spark
+                .read()
+                .textFile(outputPath)
+                .map(as(Dataset.class), Encoders.bean(Dataset.class));
+        Assertions.assertEquals(3, d.count());
+        
+    }
+
+    private static <R> MapFunction<String, R> as(Class<R> clazz) {
+        return s -> OBJECT_MAPPER.readValue(s, clazz);
+    }
+}
diff --git a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/entities/dataset/dataset.json b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/entities/dataset/dataset.json
new file mode 100644
index 0000000000..bf2f2d9639
--- /dev/null
+++ b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/entities/dataset/dataset.json
@@ -0,0 +1,3 @@
+{"author":[{"affiliation":[],"fullname":"Greenough, B","name":"B","pid":[],"rank":1,"surname":"Greenough"}],"bestaccessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"collectedfrom":[{"key":"10|re3data_____::4c4416659cb74c2e0e891a883a047cbc","value":"Bacterial Protein Interaction Database - DUP"}],"context":[],"contributor":[],"country":[],"coverage":[],"dataInfo":{"deletedbyinference":true,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"dateofcollection":"2021-09-25T10:55:00.639Z","dateoftransformation":"2021-09-25T11:00:04.201Z","description":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"value":"Heritage Education"}],"externalReference":[],"extraInfo":[],"format":[],"fulltext":[],"geolocation":[],"id":"50|doi_________::09821844208a5cd6300b2bfb13bca1b9","instance":[{"accessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"pid":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"urn","classname":"urn","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"urn:nbn:nl:ui:13-59-cjhf"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.17632/96bpgw5j9d.1"}],"collectedfrom":{"key":"10|re3data_____::4c4416659cb74c2e0e891a883a047cbc","value":"Bacterial Protein Interaction Database - DUP"},"hostedby":{"key":"10|openaire____::c6df70599aa984f16ee52b4b86d2e89f","value":"DANS (Data Archiving and Networked Services)"},"instancetype":{"classid":"0021","classname":"Dataset","schemeid":"dnet:publication_resource","schemename":"dnet:publication_resource"},"alternateIdentifier":[],"refereed":{"classid":"0000","classname":"Unknown","schemeid":"dnet:review_levels","schemename":"dnet:review_levels"},"url":["","http://dx.doi.org/10.17632/96bpgw5j9d.1"]}],"language":{"classid":"und","classname":"Undetermined","schemeid":"dnet:languages","schemename":"dnet:languages"},"lastupdatetimestamp":1635434801681,"oaiprovenance":{"originDescription":{"altered":true,"baseURL":"http%3A%2F%2Fservices.nod.dans.knaw.nl%2Foa-cerif","datestamp":"2021-08-16T15:29:45Z","harvestDate":"2021-09-25T10:55:00.639Z","identifier":"oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:211323","metadataNamespace":""}},"originalId":["50|DansKnawCris::09821844208a5cd6300b2bfb13bca1b9","oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:211323"],"pid":[],"relevantdate":[],"resourcetype":{"classid":"0021","classname":"0021","schemeid":"dnet:dataCite_resource","schemename":"dnet:dataCite_resource"},"resulttype":{"classid":"dataset","classname":"dataset","schemeid":"dnet:result_typologies","schemename":"dnet:result_typologies"},"source":[],"subject":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Interdisciplinary sciences"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Interdisciplinary sciences"}],"title":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"main title","classname":"main title","schemeid":"dnet:dataCite_title","schemename":"dnet:dataCite_title"},"value":"Heritage Education"}]}
+{"author":[{"affiliation":[],"fullname":"Keijers, D.M.G.","name":"D.M.G.","pid":[],"rank":1,"surname":"Keijers"}],"bestaccessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"collectedfrom":[{"key":"10|opendoar____::788b4ac1e172d8e520c2b9461c0a3d35","value":"FILUR DATA - DUP"}],"context":[],"contributor":[],"country":[],"coverage":[],"dataInfo":{"deletedbyinference":true,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"dateofcollection":"2021-09-25T10:41:59.767Z","dateoftransformation":"2021-09-25T11:00:19.238Z","description":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"value":"onderzoeksrapport"}],"externalReference":[],"extraInfo":[],"format":[],"fulltext":[],"geolocation":[],"id":"50|DansKnawCris::0dd644304b7116e8e58da3a5e3adc37a","instance":[{"accessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"pid":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"urn","classname":"urn","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"urn:nbn:nl:ui:13-das-fkq"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.17026/dans-xsw-qtnx"}],"collectedfrom":{"key":"10|opendoar____::788b4ac1e172d8e520c2b9461c0a3d35","value":"FILUR DATA - DUP"},"hostedby":{"key":"10|re3data_____::6ffd7bc058f762912dc494cd9c175341","value":"depositar - DUP"},"instancetype":{"classid":"0021","classname":"Dataset","schemeid":"dnet:publication_resource","schemename":"dnet:publication_resource"},"alternateIdentifier":[],"refereed":{"classid":"0000","classname":"Unknown","schemeid":"dnet:review_levels","schemename":"dnet:review_levels"},"url":["","http://dx.doi.org/10.17026/dans-xsw-qtnx"]}],"language":{"classid":"dut/nld","classname":"Dutch; Flemish","schemeid":"dnet:languages","schemename":"dnet:languages"},"lastupdatetimestamp":1635434847381,"oaiprovenance":{"originDescription":{"altered":true,"baseURL":"http%3A%2F%2Fservices.nod.dans.knaw.nl%2Foa-cerif","datestamp":"2021-08-16T13:53:29Z","harvestDate":"2021-09-25T10:41:59.767Z","identifier":"oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:20759","metadataNamespace":""}},"originalId":["oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:20759","50|DansKnawCris::0dd644304b7116e8e58da3a5e3adc37a"],"pid":[],"relevantdate":[],"resourcetype":{"classid":"0021","classname":"0021","schemeid":"dnet:dataCite_resource","schemename":"dnet:dataCite_resource"},"resulttype":{"classid":"dataset","classname":"dataset","schemeid":"dnet:result_typologies","schemename":"dnet:result_typologies"},"source":[],"subject":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"PROSPECTIE"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Archaeology"}],"title":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"main title","classname":"main title","schemeid":"dnet:dataCite_title","schemename":"dnet:dataCite_title"},"value":"Plangebied Lange Ekker te Vessem, gemeente Eersel"}]}
+{"author":[],"bestaccessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"collectedfrom":[{"key":"10|openaire____::c6df70599aa984f16ee52b4b86d2e89f","value":"DANS (Data Archiving and Networked Services)"}],"context":[],"contributor":[],"country":[],"coverage":[],"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"dateofcollection":"2021-09-25T10:43:13.768Z","dateoftransformation":"2021-09-25T11:01:22.863Z","description":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"value":"This find is registered at Portable Antiquities of the Netherlands with number PAN-00054604"}],"externalReference":[],"extraInfo":[],"format":[],"fulltext":[],"geolocation":[],"id":"50|DansKnawCris::203a27996ddc0fd1948258e5b7dec61c","instance":[{"accessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes"},"pid":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"urn","classname":"urn","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"urn:nbn:nl:ui:13-a7-hwgy"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.17026/dans-x3z-fsq5"}],"collectedfrom":{"key":"10|openaire____::c6df70599aa984f16ee52b4b86d2e89f","value":"DANS (Data Archiving and Networked Services)"},"hostedby":{"key":"10|openaire____::c6df70599aa984f16ee52b4b86d2e89f","value":"DANS (Data Archiving and Networked Services)"},"instancetype":{"classid":"0021","classname":"Dataset","schemeid":"dnet:publication_resource","schemename":"dnet:publication_resource"},"alternateIdentifier":[],"refereed":{"classid":"0000","classname":"Unknown","schemeid":"dnet:review_levels","schemename":"dnet:review_levels"},"url":["","http://dx.doi.org/10.17026/dans-x3z-fsq5"]}],"language":{"classid":"eng","classname":"English","schemeid":"dnet:languages","schemename":"dnet:languages"},"lastupdatetimestamp":1635434508886,"oaiprovenance":{"originDescription":{"altered":true,"baseURL":"http%3A%2F%2Fservices.nod.dans.knaw.nl%2Foa-cerif","datestamp":"2021-08-16T14:01:37Z","harvestDate":"2021-09-25T10:43:13.768Z","identifier":"oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:129566","metadataNamespace":""}},"originalId":["oai:services.nod.dans.knaw.nl:Products/dans:oai:easy.dans.knaw.nl:easy-dataset:129566","50|DansKnawCris::203a27996ddc0fd1948258e5b7dec61c"],"pid":[],"relevantdate":[],"resourcetype":{"classid":"0021","classname":"0021","schemeid":"dnet:dataCite_resource","schemename":"dnet:dataCite_resource"},"resulttype":{"classid":"dataset","classname":"dataset","schemeid":"dnet:result_typologies","schemename":"dnet:result_typologies"},"source":[],"subject":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"early medieval enamelled disc brooch variant A9"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Broader Match: disc brooches"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Broader Match: schijffibula - geemailleerd"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"metal"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"copper alloy"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Temporal coverage: Early Middle Ages C"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Temporal coverage: Early Middle Ages D"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Temporal coverage: 800 until 1000"},{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"keyword","classname":"keyword","schemeid":"dnet:subject_classification_typologies","schemename":"dnet:subject_classification_typologies"},"value":"Archaeology"}],"title":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"","inferred":false,"invisible":false,"provenanceaction":{"classid":"sysimport:crosswalk:datasetarchive","classname":"Harvested","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":"0.9"},"qualifier":{"classid":"main title","classname":"main title","schemeid":"dnet:dataCite_title","schemename":"dnet:dataCite_title"},"value":"PAN-00054604 - early medieval enamelled disc brooch variant A9"}]}
\ No newline at end of file
diff --git a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/masterduplicate.json b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/masterduplicate.json
new file mode 100644
index 0000000000..b63cfe6b31
--- /dev/null
+++ b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/cfhb/masterduplicate.json
@@ -0,0 +1,4 @@
+{ "duplicateId" :  "10|re3data_____::4c4416659cb74c2e0e891a883a047cbc", "masterId" : "10|fairsharing_::a29d1598024f9e87beab4b98411d48ce", "masterName" : "Bacterial Protein Interaction Database" }
+{ "duplicateId" :  "10|opendoar____::788b4ac1e172d8e520c2b9461c0a3d35", "masterId" : "10|re3data_____::fc1db64b3964826913b1e9eafe830490", "masterName" : "FULIR Data" }
+{ "duplicateId" :  "10|re3data_____::6ffd7bc058f762912dc494cd9c175341", "masterId" : "10|fairsharing_::3f647cadf56541fb9513cb63ec370187", "masterName" : "depositar" }
+{ "duplicateId" :  "10|scindeksserb::07022f78a8cc6d1171092454ecdbb47c", "masterId" : "10|doajarticles::07022f78a8cc6d1171092454ecdbb47c", "masterName" : "Artefact" }
\ No newline at end of file