Triple
T23726146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benny Goodman Carnegie Hall Jazz Concert |
E586280
|
entity |
| Predicate | featuredSoloist |
P83545
|
FINISHED |
| Object | Benny Goodman |
—
|
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: Benny Goodman | Statement: [Benny Goodman Carnegie Hall Jazz Concert, featuredSoloist, Benny Goodman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredSoloist Context triple: [Benny Goodman Carnegie Hall Jazz Concert, featuredSoloist, Benny Goodman]
-
A.
soloist
Indicates that an entity performs or appears alone as the primary featured performer in an artistic or musical context.
-
B.
featuresMusician
Indicates that something (such as a work, event, or recording) prominently includes or showcases a particular musician.
-
C.
featuresSoloPerformancesBy
chosen
Indicates that the subject includes or showcases solo performances carried out by the specified performer or performers.
-
D.
soloistRole
Indicates that an entity has the role of performing as a soloist within a work, event, or performance.
-
E.
featuresArtistAs
Indicates that one entity includes or presents another entity in the role of an artist (e.g., a work, event, or product featuring a specific artist).
- 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b915a888819088e92f99711e8120 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:08 p.m.