From 75a9d9b9ade3d97dfb50ea0f989b9658866900a2 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <matt@explosion.ai>
Date: Wed, 28 May 2025 17:04:23 +0200
Subject: [PATCH] Test and fix issue13769

---
 spacy/tests/doc/test_span.py | 14 +++++++++++++-
 spacy/tokens/span.pyx        |  9 +++++----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/spacy/tests/doc/test_span.py b/spacy/tests/doc/test_span.py
index 98a74bc21..38e77de29 100644
--- a/spacy/tests/doc/test_span.py
+++ b/spacy/tests/doc/test_span.py
@@ -49,7 +49,7 @@ def doc_not_parsed(en_tokenizer):
 def test_issue1537():
     """Test that Span.as_doc() doesn't segfault."""
     string = "The sky is blue . The man is pink . The dog is purple ."
-    doc = Doc(Vocab(), words=string.split())
+    doc = Doc(Vocab(), words=list(string.split()))
     doc[0].sent_start = True
     for word in doc[1:]:
         if word.nbor(-1).text == ".":
@@ -225,6 +225,18 @@ def test_spans_span_sent(doc, doc_not_parsed):
     assert doc_not_parsed[10:14].sent == doc_not_parsed[5:]
 
 
+def test_issue13769():
+    # Test issue 13769: Incorrect output of span.sents when final token is a sentence outside of the span.
+    doc = Doc(Vocab(), words=list("This is a sentence . This is another sentence . Third".split()))
+    doc[0].is_sent_start = True
+    doc[5].is_sent_start = True
+    doc[10].is_sent_start = True
+    doc.ents = [('ENTITY', 7, 9)] # "another sentence" phrase in the second sentence
+    entity = doc.ents[0]
+    ent_sents = list(entity.sents)
+    assert len(ent_sents) == 1
+
+
 @pytest.mark.parametrize(
     "start,end,expected_sentence",
     [
diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx
index 64b8d7c6c..a7faf0d62 100644
--- a/spacy/tokens/span.pyx
+++ b/spacy/tokens/span.pyx
@@ -479,10 +479,11 @@ cdef class Span:
                         break
                 elif i == self.doc.length - 1:
                     yield Span(self.doc, start, self.doc.length)
-
-            # Ensure that trailing parts of the Span instance are included in last element of .sents.
-            if start == self.doc.length - 1:
-                yield Span(self.doc, start, self.doc.length)
+            else:
+                # Ensure that trailing parts of the Span instance are included in last element of .sents.
+                # We only want to do this if we didn't break above
+                if start == self.doc.length - 1:
+                    yield Span(self.doc, start, self.doc.length)
 
     @property
     def ents(self):