Triple
T22767478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Crow |
E563166
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Michael Wincott |
—
|
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: Michael Wincott | Statement: [The Crow, castMember, Michael Wincott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Wincott Context triple: [The Crow, castMember, Michael Wincott]
-
A.
Michael Wincott
chosen
Michael Wincott is a Canadian character actor known for his distinctive raspy voice and memorable villainous roles in films such as The Crow, Robin Hood: Prince of Thieves, and Nope.
-
B.
Charles Newirth
Charles Newirth is a veteran American film producer known for his work on major studio features and collaborations on high-profile Hollywood projects.
-
C.
Michael Walters
Michael Walters is a professional Australian rules footballer best known for his career with the Fremantle Dockers in the Australian Football League.
-
D.
Matthew Weisman
Matthew Weisman is a creator and writer best known for developing the character Jenny Matrix.
-
E.
Matthew Weisman
Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a81d3348190b005a43a5e03d406 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:27 p.m.