Triple
T19993903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dave Kelly |
E494133
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Bounty Killer |
—
|
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: Bounty Killer | Statement: [Dave Kelly, collaboratedWith, Bounty Killer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bounty Killer Context triple: [Dave Kelly, collaboratedWith, Bounty Killer]
-
A.
Bounty Killer
chosen
Bounty Killer is a Jamaican dancehall and reggae deejay known for his gritty delivery, influential 1990s hits, and role in shaping hardcore dancehall music.
-
B.
The Bounty Killer
The Bounty Killer is a Western novel by American author Marvin H. Albert, known for its gritty portrayal of frontier justice and professional manhunters in the Old West.
-
C.
Bounty
Bounty is a popular Procter & Gamble paper towel brand known for its high absorbency and durability.
-
D.
Bounty
Bounty is a chocolate bar brand consisting of coconut filling coated in milk or dark chocolate, produced and marketed by Mars, Incorporated.
-
E.
Bounty Hunters
Bounty Hunters is a British action-comedy television series that blends crime caper antics with dark humor and features Charity Wakefield among its ensemble cast.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe2036c8190b9f313215ad44e87 |
completed | April 20, 2026, 5:18 p.m. |
Created at: April 11, 2026, 3:31 p.m.