lets try to repair inconsistenciesse

generic_ner.py

@@ -73,6 +73,11 @@ def get_entities(tokens, tags, confidences, text):
     tags = [tag.replace("S-", "B-").replace("E-", "I-") for tag in tags]
     pos_tags = [pos for token, pos in pos_tag(tokens)]
 
+    for i in range(1, len(tags)):
+        # If a 'B-' tag is followed by another 'B-' without an 'O' in between, change the second to 'I-'
+        if tags[i].startswith("B-") and tags[i - 1].startswith("I-"):
+            tags[i] = "I-" + tags[i][2:]  # Change 'B-' to 'I-' for the same entity type
+
     conlltags = [(token, pos, tg) for token, pos, tg in zip(tokens, pos_tags, tags)]
     ne_tree = conlltags2tree(conlltags)