Triple
T10325612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tully |
E242753
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | A. J. Dix |
E241139
|
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: A. J. Dix | Statement: [Tully, producer, A. J. Dix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A. J. Dix Context triple: [Tully, producer, A. J. Dix]
-
A.
A. J. Dix
chosen
A. J. Dix is a film producer known for her work on the action thriller "Atomic Blonde."
-
B.
Talbot Jennings
Talbot Jennings was an American screenwriter known for his work on notable mid-20th-century films, including several acclaimed literary and historical adaptations.
-
C.
Calvert DeForest
Calvert DeForest was an American character actor and comedian best known for his quirky, deadpan appearances as "Larry 'Bud' Melman" on David Letterman's late-night shows.
-
D.
C. T. Wilkins
C. T. Wilkins was an aircraft designer best known for his role in creating the British World War II de Havilland Mosquito multirole combat aircraft.
-
E.
J. K. Reynolds
J. K. Reynolds is a technical author known for contributing to Internet standards documentation, including RFC 973.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7cd76348190b93562112300acfc |
completed | April 7, 2026, 10:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71da93b988190ad568b0677b5d344 |
completed | April 9, 2026, 3:31 a.m. |
Created at: April 6, 2026, 11:51 a.m.