Triple
T32407272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beyoncé’s 2018 Coachella performance |
E828116
|
entity |
| Predicate | audioRelease |
P117080
|
FINISHED |
| Object | Homecoming: The Live Album |
—
|
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: Homecoming: The Live Album | Statement: [Beyoncé’s 2018 Coachella performance, audioRelease, Homecoming: The Live Album]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: audioRelease Context triple: [Beyoncé’s 2018 Coachella performance, audioRelease, Homecoming: The Live Album]
-
A.
isAudioReleaseOf
chosen
Indicates that one entity is an audio-format publication or version corresponding to another entity (such as a work, event, or release) from which it is derived.
-
B.
volumeReleased
Indicates that a specific volume (such as a book, issue, or installment) has been officially released or made publicly available.
-
C.
releaseOf
Indicates the act or event of something being set free, made available, or discharged from a prior state of containment, control, or restriction.
-
D.
audioOnlyFeatureIntroduced
Indicates that a feature has been introduced which supports or enables audio-only functionality, without accompanying visual content.
-
E.
audioStack
Indicates that one audio element is layered or queued on top of another within an ordered audio sequence or mix.
- 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_69f34919f300819092b541c6277cd68a |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c24ca0f08190a5b2c1d32205eaee |
completed | May 3, 2026, 3:34 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:53 a.m.