Triple
T21489023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Henderson |
E530186
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Andrew Hill |
—
|
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: Andrew Hill | Statement: [Joe Henderson, associatedAct, Andrew Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Hill Context triple: [Joe Henderson, associatedAct, Andrew Hill]
-
A.
Andrew Hill
chosen
Andrew Hill was an influential American jazz pianist and composer known for his innovative, avant-garde work on the Blue Note label in the 1960s.
-
B.
William Henderson
William Henderson is a fictional police inspector, often portrayed as a Gotham City law enforcement officer and ally of Superman and other DC Comics superheroes.
-
C.
William Henderson
William Henderson was an early settler and landowner after whom the town of Henderson in Jefferson County, New York, was named.
-
D.
John Hilliard
John Hilliard is a British conceptual artist and photographer known for his experimental works that explore the nature of photographic representation and perception.
-
E.
Hamilton Hodell
Hamilton Hodell is a prominent London-based talent agency representing high-profile actors and creatives in film, television, and theatre.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea39e73081908e8d14118f9d1e03 |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:22 p.m.