Triple
T23406443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol (2015 film) |
E559946
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Kevin Crowley |
—
|
NE NERFINISHED |
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: Kevin Crowley | Statement: [Carol (2015 film), castMember, Kevin Crowley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Crowley Context triple: [Carol (2015 film), castMember, Kevin Crowley]
-
A.
Kevin Crowley
chosen
Kevin Crowley is an actor known for his role in the film "Can't Hurry Love."
-
B.
William Regal
William Regal is an English professional wrestling veteran and authority figure renowned for his technical in-ring style, influential training of younger wrestlers, and prominent roles in WWE.
-
C.
Kevin Kingston
Kevin Kingston is a young boy character in the family road-trip comedy film "Are We There Yet?"
-
D.
Scott Steiner
Scott Steiner is an American professional wrestler known for his muscular physique, intense persona, and successful runs in major promotions like WCW and WWE.
-
E.
Michael Cole
Michael Cole is a longtime professional wrestling commentator best known as the lead play-by-play announcer for WWE.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50e607c8190ba0a22e89862a2d9 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.