diff --git a/haystack/document_stores/sql.py b/haystack/document_stores/sql.py
index 5bafd0cdf..9a7cd0e28 100644
--- a/haystack/document_stores/sql.py
+++ b/haystack/document_stores/sql.py
@@ -406,24 +406,23 @@ class SQLDocumentStore(BaseDocumentStore):
                         meta_orms.append(MetaDocumentORM(name=key, value=value))
                     except TypeError as ex:
                         logger.error("Document %s - %s", doc.id, ex)
-                doc_mapping = {
-                    "id": doc.id,
-                    "content": doc.to_dict()["content"],
-                    "content_type": doc.content_type,
-                    "vector_id": vector_id,
-                    "meta": meta_orms,
-                    "index": index,
-                }
+                doc_orm = DocumentORM(
+                    id=doc.id,
+                    content=doc.to_dict()["content"],
+                    content_type=doc.content_type,
+                    vector_id=vector_id,
+                    meta=meta_orms,
+                    index=index,
+                )
                 if duplicate_documents == "overwrite":
-                    doc_orm = DocumentORM(**doc_mapping)
                     # First old meta data cleaning is required
                     self.session.query(MetaDocumentORM).filter_by(document_id=doc.id).delete()
                     self.session.merge(doc_orm)
                 else:
-                    docs_orm.append(doc_mapping)
+                    docs_orm.append(doc_orm)
 
             if docs_orm:
-                self.session.bulk_insert_mappings(DocumentORM, docs_orm)
+                self.session.add_all(docs_orm)
 
             try:
                 self.session.commit()
diff --git a/test/document_stores/test_base.py b/test/document_stores/test_base.py
index 47a712bea..c983c58f5 100644
--- a/test/document_stores/test_base.py
+++ b/test/document_stores/test_base.py
@@ -82,11 +82,12 @@ class DocumentStoreBaseTestAbstract:
     @pytest.mark.integration
     def test_write_with_duplicate_doc_ids(self, ds):
         duplicate_documents = [
-            Document(content="Doc1", id_hash_keys=["content"]),
-            Document(content="Doc1", id_hash_keys=["content"]),
+            Document(content="Doc1", id_hash_keys=["content"], meta={"key1": "value1"}),
+            Document(content="Doc1", id_hash_keys=["content"], meta={"key1": "value1"}),
         ]
         ds.write_documents(duplicate_documents, duplicate_documents="skip")
         assert len(ds.get_all_documents()) == 1
+        assert ds.get_all_documents()[0] == duplicate_documents[0]
         with pytest.raises(Exception):
             ds.write_documents(duplicate_documents, duplicate_documents="fail")