Triple
T28145264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miles Davis All Stars, Volume 1 |
E714459
|
entity |
| Predicate | contributorRole_J. J. Johnson |
P181313
|
FINISHED |
| Object | trombone |
—
|
LITERAL 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: trombone | Statement: [Miles Davis All Stars, Volume 1, contributorRole_J. J. Johnson, trombone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contributorRole_J. J. Johnson Context triple: [Miles Davis All Stars, Volume 1, contributorRole_J. J. Johnson, trombone]
-
A.
roleOfJohn Fred Young
Indicates that John holds or performs the role associated with Fred Young.
-
B.
notableWorkRole
Indicates that a person’s role or position is specifically associated with the creation, performance, or contribution to a notable work.
-
C.
creativeContributor
Indicates a relationship where an entity plays an active role in originating, designing, or shaping the creative content or form of another entity.
-
D.
producedPerson
Indicates that one entity created, generated, or brought into existence the person referenced by the other entity.
-
E.
roleInMadMen
Indicates that one entity has a specific role or character in the television series "Mad Men" in relation to another entity.
- F. None of above. chosen
Provenance (4 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_69efd6b033208190bf74f80a147e2092 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_69f7688cea58819098bdfd7c80df7634 |
completed | May 3, 2026, 3:23 p.m. |
Created at: April 27, 2026, 9:56 p.m.