Triple
T8628102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brett Cullen |
E204329
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cullen |
E55279
|
NE FINISHED |
How this triple was built (2 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: Cullen | Statement: [Brett Cullen, familyName, Cullen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cullen Context triple: [Brett Cullen, familyName, Cullen]
-
A.
Cullen
chosen
Cullen is a surname of Irish and Scottish origin borne by various notable individuals across politics, sports, and the arts.
-
B.
Callen
Callen is a fictional undercover operative and lead character in the television series "NCIS: Los Angeles," known for his mysterious past and exceptional investigative skills.
-
C.
Callian
Callian is a picturesque commune in southeastern France’s Var department, known for its medieval hilltop village and views over the Pays de Fayence.
-
D.
Curran
Curran is a surname of Irish origin borne by various notable individuals in politics, sports, and the arts.
-
E.
Rennahan
Rennahan is a surname most notably associated with Ray Rennahan, an American cinematographer known for his pioneering work with Technicolor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc472ccc0c81908e0708c94a7cbe65 |
completed | March 31, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebbf918f08190a9b0469eae8e0e0d |
completed | April 2, 2026, 6:56 p.m. |
Created at: March 30, 2026, 6:27 p.m.