diff --git a/spacy/gold/gold_io.pyx b/spacy/gold/gold_io.pyx
index 1c66ff5e9..967bee060 100644
--- a/spacy/gold/gold_io.pyx
+++ b/spacy/gold/gold_io.pyx
@@ -53,7 +53,7 @@ def docs_to_json(docs, id=0, ner_missing_tag="O"):
         for j, sent in enumerate(doc.sents):
             json_sent = {"tokens": [], "brackets": []}
             for token in sent:
-                json_token = {"id": token.i, "orth": token.text}
+                json_token = {"id": token.i, "orth": token.text, "space": token.whitespace_}
                 if doc.is_tagged:
                     json_token["tag"] = token.tag_
                     json_token["pos"] = token.pos_
@@ -91,6 +91,7 @@ def json_to_annotations(doc):
     for paragraph in doc["paragraphs"]:
         example = {"text": paragraph.get("raw", None)}
         words = []
+        spaces = []
         ids = []
         tags = []
         pos = []
@@ -104,6 +105,7 @@ def json_to_annotations(doc):
             sent_start_i = len(words)
             for i, token in enumerate(sent["tokens"]):
                 words.append(token["orth"])
+                spaces.append(token["space"])
                 ids.append(token.get('id', sent_start_i + i))
                 tags.append(token.get('tag', "-"))
                 pos.append(token.get("pos", ""))
@@ -126,6 +128,7 @@ def json_to_annotations(doc):
         example["token_annotation"] = dict(
             ids=ids,
             words=words,
+            spaces=spaces,
             tags=tags,
             pos=pos,
             morphs=morphs,
diff --git a/spacy/tests/test_gold.py b/spacy/tests/test_gold.py
index 5fd060088..83489799c 100644
--- a/spacy/tests/test_gold.py
+++ b/spacy/tests/test_gold.py
@@ -262,7 +262,7 @@ def test_roundtrip_docs_to_json(doc):
     deps = [t.dep_ for t in doc]
     heads = [t.head.i for t in doc]
     cats = doc.cats
-    ents = doc.ents
+    ents = [(e.start_char, e.end_char, e.label_) for e in doc.ents]
 
     # roundtrip to JSON
     with make_tempdir() as tmpdir:
@@ -272,7 +272,7 @@ def test_roundtrip_docs_to_json(doc):
 
         reloaded_example = next(goldcorpus.dev_dataset(nlp=nlp))
         assert len(doc) == goldcorpus.count_train()
-    assert text == reloaded_example.predicted.text
+    assert text == reloaded_example.reference.text
     assert idx == [t.idx for t in reloaded_example.reference]
     assert tags == [t.tag_ for t in reloaded_example.reference]
     assert pos == [t.pos_ for t in reloaded_example.reference]
@@ -280,7 +280,7 @@ def test_roundtrip_docs_to_json(doc):
     assert lemmas == [t.lemma_ for t in reloaded_example.reference]
     assert deps == [t.dep_ for t in reloaded_example.reference]
     assert heads == [t.head.i for t in reloaded_example.reference]
-    assert ents == reloaded_example.reference.ents
+    assert ents == [(e.start_char, e.end_char, e.label_) for e in  reloaded_example.reference.ents]
     assert "TRAVEL" in reloaded_example.reference.cats
     assert "BAKING" in reloaded_example.reference.cats
     assert cats["TRAVEL"] == reloaded_example.reference.cats["TRAVEL"]