Triple
T20090572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sink the Bismarck! |
E496256
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | John Brabourne |
—
|
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: John Brabourne | Statement: [Sink the Bismarck!, producer, John Brabourne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Brabourne Context triple: [Sink the Bismarck!, producer, John Brabourne]
-
A.
John Brabourne
chosen
John Brabourne was a British film and television producer, known for his adaptations of classic literature and for being the son-in-law of Lord Mountbatten.
-
B.
Paul Brindley
Paul Brindley is an English musician best known as the bassist and co-founder of the alternative rock band The Sundays.
-
C.
Roy Barraclough
Roy Barraclough was an English actor and comedian best known for his long-running role as Alec Gilroy in the ITV soap opera Coronation Street.
-
D.
Anthony Bevan
Anthony Bevan was a British orientalist and scholar of Semitic languages known for his contributions to the study of Arabic and Hebrew texts.
-
E.
Ian Burchnall
Ian Burchnall is an English football manager known for his coaching roles in Scandinavian and lower-league English clubs.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655e1ef0819095f40a1ce2eb17b7 |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 11:20 p.m.