Triple
T12441473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Matter of Life and Death |
E297280
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Allan Gray |
E361928
|
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: Allan Gray | Statement: [A Matter of Life and Death, composer, Allan Gray]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Allan Gray Context triple: [A Matter of Life and Death, composer, Allan Gray]
-
A.
Allan Gray
chosen
Allan Gray was a British film composer known for his scores for classic films of the 1930s and 1940s.
-
B.
Crispin Odey
Crispin Odey is a British hedge fund manager and founder of Odey Asset Management, known for his high-profile bets in financial markets and prominent role in the UK investment industry.
-
C.
Edward Jones
Edward Jones is a Canadian architect known for his work on prominent civic and public buildings, including the Mississauga Civic Centre.
-
D.
Edward Jones
Edward Jones was an American statistician and co-founder of Dow Jones & Company, best known for helping create the Dow Jones Industrial Average.
-
E.
Kevin King Templeton
Kevin King Templeton is a film producer best known for his longtime collaboration with Sylvester Stallone on action and sports drama films.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d8ecb6c8190a19cbf9de31cabbd |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f0ea1e48190a11cf94797290156 |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:55 p.m.