Triple
T17068722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Israel Crosby |
E414156
|
entity |
| Predicate | playedInEnsemble |
P49020
|
FINISHED |
| Object | piano trio format |
—
|
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: piano trio format | Statement: [Israel Crosby, playedInEnsemble, piano trio format]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedInEnsemble Context triple: [Israel Crosby, playedInEnsemble, piano trio format]
-
A.
playedInEnsembleWith
Indicates that one entity has performed together with another as members of the same musical ensemble or group.
-
B.
partOfCastEnsembleWith
Indicates that two or more performers are members of the same cast ensemble in a shared production.
-
C.
hasEnsembleCast
Indicates that a work features an ensemble cast, meaning multiple principal performers share roughly equal prominence rather than having a single clear lead.
-
D.
alsoPlayedIn
Indicates that an entity (such as a person or performer) participated or appeared in another work, production, or context in addition to the one already referenced.
-
E.
isPartOfEnsemble
chosen
Indicates that an entity belongs to, or is a member of, a larger group or ensemble.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbbeb2a48190a733a4cc829c16de |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.