Triple
T21877502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hard Attack |
E540186
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Kenny Kerner |
—
|
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: Kenny Kerner | Statement: [Hard Attack, producer, Kenny Kerner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kenny Kerner Context triple: [Hard Attack, producer, Kenny Kerner]
-
A.
Kenny Kerner
chosen
Kenny Kerner was an American record producer and music industry figure best known for his work in the 1970s rock and pop scenes, including early production for the band Kiss.
-
B.
Jack Keller
Jack Keller was an American songwriter and producer associated with the Brill Building era, known for co-writing numerous pop hits in the 1960s.
-
C.
Jim Kripps
Jim Kripps is a fictional character appearing in the work titled "The Silence."
-
D.
Grant Kester
Grant Kester is an American art historian and critic known for his influential writings on socially engaged art and dialogical aesthetics.
-
E.
Bill Stumpf
Bill Stumpf was an American industrial designer best known for co-designing iconic ergonomic office chairs such as the Aeron for Herman Miller.
- 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_69e0c479a98081908ce333853fdd4348 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f33c012c819096d0f7b2ffdc7a2f |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 7:02 p.m.