diff --git a/spacy/cli/convert.py b/spacy/cli/convert.py
index 4e3975bda..c8c5a3902 100644
--- a/spacy/cli/convert.py
+++ b/spacy/cli/convert.py
@@ -135,7 +135,7 @@ def convert(
 
 def _print_docs_to_stdout(docs, output_type):
     if output_type == "json":
-        srsly.write_json("-", docs_to_json(docs))
+        srsly.write_json("-", [docs_to_json(docs)])
     else:
         sys.stdout.buffer.write(DocBin(docs=docs, store_user_data=True).to_bytes())
 
@@ -144,7 +144,7 @@ def _write_docs_to_file(docs, output_file, output_type):
     if not output_file.parent.exists():
         output_file.parent.mkdir(parents=True)
     if output_type == "json":
-        srsly.write_json(output_file, docs_to_json(docs))
+        srsly.write_json(output_file, [docs_to_json(docs)])
     else:
         data = DocBin(docs=docs, store_user_data=True).to_bytes()
         with output_file.open("wb") as file_:
diff --git a/spacy/gold/gold_io.pyx b/spacy/gold/gold_io.pyx
index fbf8ebea7..5dc39eb31 100644
--- a/spacy/gold/gold_io.pyx
+++ b/spacy/gold/gold_io.pyx
@@ -24,14 +24,15 @@ def docs_to_json(docs, doc_id=0, ner_missing_tag="O"):
         for cat, val in doc.cats.items():
             json_cat = {"label": cat, "value": val}
             json_para["cats"].append(json_cat)
+        # warning: entities information is currently duplicated as
+        # doc-level "entities" and token-level "ner"
         for ent in doc.ents:
             ent_tuple = (ent.start_char, ent.end_char, ent.label_)
             json_para["entities"].append(ent_tuple)
             if ent.kb_id_:
                 link_dict = {(ent.start_char, ent.end_char): {ent.kb_id_: 1.0}}
                 json_para["links"].append(link_dict)
-        ent_offsets = [(e.start_char, e.end_char, e.label_) for e in doc.ents]
-        biluo_tags = biluo_tags_from_offsets(doc, ent_offsets, missing=ner_missing_tag)
+        biluo_tags = biluo_tags_from_offsets(doc, json_para["entities"], missing=ner_missing_tag)
         for j, sent in enumerate(doc.sents):
             json_sent = {"tokens": [], "brackets": []}
             for token in sent:
@@ -44,6 +45,7 @@ def docs_to_json(docs, doc_id=0, ner_missing_tag="O"):
                 if doc.is_parsed:
                     json_token["head"] = token.head.i-token.i
                     json_token["dep"] = token.dep_
+                json_token["ner"] = biluo_tags[token.i]
                 json_sent["tokens"].append(json_token)
             json_para["sentences"].append(json_sent)
         json_doc["paragraphs"].append(json_para)