Triple
T7497882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broken Trail |
E177178
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Butch Kaplan |
E671779
|
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: Butch Kaplan | Statement: [Broken Trail, producer, Butch Kaplan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Butch Kaplan Context triple: [Broken Trail, producer, Butch Kaplan]
-
A.
Butch Kaplan
chosen
Butch Kaplan is a film and television producer known for his work on projects such as the Western miniseries "Broken Trail."
-
B.
Bud Brigman
Bud Brigman is the deep-sea oil rig foreman and central protagonist in James Cameron's science fiction film "The Abyss."
-
C.
David Bonderman
David Bonderman is an American billionaire businessman and private equity investor, best known as a founding partner of TPG Capital and as a prominent owner of major professional sports franchises.
-
D.
Sol Kaplan
Sol Kaplan was an American composer best known for his film and television scores, including work in mid-20th-century Hollywood.
-
E.
Hank Kaplan
Hank Kaplan is a fictional character from the American medical drama television series "Nurses."
- 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_69c69f2696688190915a8458f2398211 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5963d98819098275b161848d2d4 |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c89a7aada08190b241c078871dc864 |
completed | March 29, 2026, 3:20 a.m. |
Created at: March 27, 2026, 3:44 p.m.