Triple
T10366367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darkest Hour |
E244260
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Tim Bevan |
E154126
|
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: Tim Bevan | Statement: [Darkest Hour, producer, Tim Bevan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tim Bevan Context triple: [Darkest Hour, producer, Tim Bevan]
-
A.
Tim Bevan
chosen
Tim Bevan is a British film producer and co-founder of Working Title Films, known for overseeing numerous acclaimed UK and international movies.
-
B.
Geoff Travis
Geoff Travis is a British music industry figure best known as the founder of the influential independent label Rough Trade Records.
-
C.
Tim Dutton
Tim Dutton is a British actor known for his work in film, television, and theatre, including roles in period dramas and literary adaptations.
-
D.
Steve McNiven
Steve McNiven is a Canadian comic book artist best known for his highly detailed work at Marvel Comics on major events and series such as "Civil War" and "Old Man Logan."
-
E.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e96f25f48190a41c8b0206b9238c |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d89f53484881909fb976efb3882b9b |
completed | April 10, 2026, 6:57 a.m. |
Created at: April 6, 2026, noon