Triple
T23152782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hard Candy |
E578363
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Art Jones |
—
|
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: Art Jones | Statement: [Hard Candy, editedBy, Art Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Art Jones Context triple: [Hard Candy, editedBy, Art Jones]
-
A.
Art Jones
chosen
Art Jones is a film editor best known for his work on the horror movie "30 Days of Night."
-
B.
Art Jones
Art Jones was an ice hockey player best known for his standout career with the Portland Buckaroos in the Western Hockey League.
-
C.
Andy Jones
Andy Jones is an entrepreneur and technologist known as a founder of the AI safety and research company Anthropic.
-
D.
Andy Jones
Andy Jones is a musician best known for his past role in the British electronic/alternative group Lo-Fidelity Allstars.
-
E.
Andy Jones
Andy Jones is the central chef protagonist in the British drama film "Boiling Point," portrayed as a highly pressured and flawed head cook navigating a chaotic restaurant service.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efaa1fc81908fb1987dbf732f46 |
completed | April 29, 2026, 4:54 a.m. |
Created at: April 17, 2026, 4:01 p.m.