Triple
T23636431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | See You at the Fair |
E583759
|
entity |
| Predicate | mainSaxophonist |
P81522
|
FINISHED |
| Object | Ben Webster |
—
|
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: Ben Webster | Statement: [See You at the Fair, mainSaxophonist, Ben Webster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainSaxophonist Context triple: [See You at the Fair, mainSaxophonist, Ben Webster]
-
A.
featuresSaxophonist
chosen
Indicates that a musical work, performance, or recording prominently includes a saxophonist as part of its featured personnel.
-
B.
tenorSaxophonistOnRecording
Indicates that the subject is the tenor saxophonist performing on the specified recording.
-
C.
primaryTrombonist
Indicates that the subject serves as the main or lead trombone player in a musical group or context.
-
D.
hasSaxophoneSolos
Indicates that one or more saxophone solo performances occur within the referenced work, event, or context.
-
E.
hasPrincipalClarinet
Indicates that an entity has another entity serving in the role of principal clarinet within its musical ensemble or organization.
- 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_69e248fe1c2c8190ac914d2442ff3d26 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b1ed03148190a14b3c81ebf7ed99 |
completed | April 29, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:47 p.m.