Triple
T21037798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Columbo |
E518235
|
entity |
| Predicate | characterNameLaterChangedTo |
P102760
|
FINISHED |
| Object | Kate Callahan |
—
|
NE NERFINISHED |
How this triple was built (3 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kate Callahan | Statement: [Mrs. Columbo, characterNameLaterChangedTo, Kate Callahan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kate Callahan Context triple: [Mrs. Columbo, characterNameLaterChangedTo, Kate Callahan]
-
A.
Kate Callahan
chosen
Kate Callahan is a fictional FBI special agent and profiler who joins the Behavioral Analysis Unit in the television series "Criminal Minds."
-
B.
Rachel O’Connor
Rachel O’Connor is a film producer known for her work on the tennis drama movie "Challengers."
-
C.
Kathleen Callahan
Kathleen Callahan is a character featured in the 2000 documentary film "American Woman," which follows the lives and experiences of several American women.
-
D.
Laura Callanan
Laura Callanan is an American arts and social impact leader best known as the founding partner of Upstart Co-Lab and as the widow of playwright Romulus Linney.
-
E.
Sarah Sullivan
Sarah Sullivan is a fictional protagonist in an American-set story, around whom the central narrative and character development revolve.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterNameLaterChangedTo Context triple: [Mrs. Columbo, characterNameLaterChangedTo, Kate Callahan]
-
A.
characterNameChange
chosen
Indicates that an entity’s character has undergone a change from one name to another.
-
B.
changedNameInHonorOf
Indicates that an entity altered its name specifically to honor or pay tribute to another entity.
-
C.
changedNameOn
Indicates that an entity altered or updated its name at a specific point in time or on a particular date.
-
D.
changedNameIn
Indicates that an entity has altered or adopted a different name within a specific context, time period, or jurisdiction.
-
E.
changedNameBy
Indicates that one entity altered or updated the name of another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcecf2508190a7647abb3c59debb |
completed | April 21, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf6728881908a2a43a5c8804a2a |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:05 p.m.