Triple
T26964264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sap |
E679128
|
entity |
| Predicate | guestVocalistOnTrack |
P93602
|
FINISHED |
| Object | Chris Cornell on "Right Turn" |
—
|
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: Chris Cornell on "Right Turn" | Statement: [Sap, guestVocalistOnTrack, Chris Cornell on "Right Turn"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guestVocalistOnTrack Context triple: [Sap, guestVocalistOnTrack, Chris Cornell on "Right Turn"]
-
A.
recordingArtistOfGuestVocalist
Indicates that an artist is the primary recording artist on a work that features another artist as a guest vocalist.
-
B.
guestVocalistIsFrontmanOf
Indicates that the guest vocalist performing on a work is also the lead singer (frontman) of the referenced band or primary musical act.
-
C.
hasGuestVocalists
chosen
Indicates that one or more guest vocalists perform vocals on a work, performance, or recording in addition to the primary artist(s).
-
D.
vocalistOnOriginalRecording
Indicates that the subject served as the vocalist on the original recording of the work or track.
-
E.
hasVocalPerformanceBy
Indicates that a vocal performance in a work or recording is performed by a specified person or group.
- 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_69eeeb4f3a448190b1e94b2d4776c16e |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f620eea9a88190aa5096c3d1fc3cad |
completed | May 2, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:34 a.m.