From 6adc15178f74529aa1c01a390ab0c09c682e2329 Mon Sep 17 00:00:00 2001
From: Raphael Mitsch <r.mitsch@outlook.com>
Date: Mon, 13 Mar 2023 14:26:14 +0100
Subject: [PATCH] Partially fix alias/mention terminology usage. Convert
 Candidate to interface.

---
 spacy/errors.py           | 2 +-
 spacy/kb/candidate.pyx    | 6 +++---
 spacy/kb/kb.pyx           | 2 +-
 spacy/kb/kb_in_memory.pyx | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/spacy/errors.py b/spacy/errors.py
index 92770b8a8..30446e7ea 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -82,7 +82,7 @@ class Warnings(metaclass=ErrorsWithCodes):
             "ignoring the duplicate entry.")
     W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be "
             "incorrect. Modify PhraseMatcher._terminal_hash to fix.")
-    W024 = ("Entity '{entity}' - mention '{mention}' combination already exists in "
+    W024 = ("Entity '{entity}' - alias '{alias}' combination already exists in "
             "the Knowledge Base.")
     W026 = ("Unable to set all sentence boundaries from dependency parses. If "
             "you are constructing a parse tree incrementally by setting "
diff --git a/spacy/kb/candidate.pyx b/spacy/kb/candidate.pyx
index 9d3a05ec8..ac19df671 100644
--- a/spacy/kb/candidate.pyx
+++ b/spacy/kb/candidate.pyx
@@ -7,7 +7,8 @@ cdef class Candidate:
     """A `Candidate` object refers to a textual mention that may or may not be resolved
     to a specific entity from a Knowledge Base. This will be used as input for the entity linking
     algorithm which will disambiguate the various candidates to the correct one.
-    Each candidate (mention, entity_id) pair is assigned a certain prior probability.
+    Each candidate, which represents a possible link between one textual mention and one entity in the knowledge base,
+    is assigned a certain prior probability.
 
     DOCS: https://spacy.io/api/kb/#candidate-init
     """
@@ -76,7 +77,6 @@ cdef class InMemoryCandidate(Candidate):
         self._prior_prob = prior_prob
         self._kb = kb
         self._mention = mention_hash
-        self._entity_id = entity_hash
         self._entity_freq = entity_freq
 
     @property
@@ -97,7 +97,7 @@ cdef class InMemoryCandidate(Candidate):
 
     @property
     def entity_id_(self) -> str:
-        return self._kb.vocab.strings[self._entity_id]
+        return self._kb.vocab.strings[self._entity_hash]
 
     @property
     def entity_freq(self) -> float:
diff --git a/spacy/kb/kb.pyx b/spacy/kb/kb.pyx
index 158c3304f..7da312863 100644
--- a/spacy/kb/kb.pyx
+++ b/spacy/kb/kb.pyx
@@ -11,7 +11,7 @@ from ..errors import Errors
 
 
 cdef class KnowledgeBase:
-    """A `KnowledgeBase` instance stores unique identifiers for entities and their textual mentions,
+    """A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases,
     to support entity linking of named entities to real-world concepts.
     This is an abstract class and requires its operations to be implemented.
 
diff --git a/spacy/kb/kb_in_memory.pyx b/spacy/kb/kb_in_memory.pyx
index 059f3a140..4ceb87888 100644
--- a/spacy/kb/kb_in_memory.pyx
+++ b/spacy/kb/kb_in_memory.pyx
@@ -22,7 +22,7 @@ from .candidate import InMemoryCandidate
 
 
 cdef class InMemoryLookupKB(KnowledgeBase):
-    """An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual mentions,
+    """An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
     to support entity linking of named entities to real-world concepts.
 
     DOCS: https://spacy.io/api/inmemorylookupkb
@@ -216,7 +216,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
 
         if is_present:
             if not ignore_warnings:
-                warnings.warn(Warnings.W024.format(entity=entity, mention=alias))
+                warnings.warn(Warnings.W024.format(entity=entity, alias=alias))
         else:
             entry_indices.push_back(int(entry_index))
             alias_entry.entry_indices = entry_indices