Triple
T28145252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miles Davis All Stars, Volume 1 |
E714459
|
entity |
| Predicate | creditedEnsembleName |
P66001
|
FINISHED |
| Object | Miles Davis All Stars |
—
|
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: Miles Davis All Stars | Statement: [Miles Davis All Stars, Volume 1, creditedEnsembleName, Miles Davis All Stars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creditedEnsembleName Context triple: [Miles Davis All Stars, Volume 1, creditedEnsembleName, Miles Davis All Stars]
-
A.
hasEnsembleCast
Indicates that a work features an ensemble cast, meaning multiple principal performers share roughly equal prominence rather than having a single clear lead.
-
B.
partOfCastEnsembleWith
Indicates that two or more performers are members of the same cast ensemble in a shared production.
-
C.
creditedIn
chosen
Indicates that an entity is acknowledged or listed as a contributor or source within a particular work, record, or context.
-
D.
creditsAre
Indicates that certain credits are assigned, attributed, or owed to a particular entity or set of entities.
-
E.
famousEnsemble
Indicates that the subject is a well-known group of performers or artists collectively recognized for their work.
- F. None of above.
Provenance (3 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_69f6417146c081908043ee0e8982e005 |
completed | May 2, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:56 p.m.