Triple
T12296900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lynda Laurence |
E293110
|
entity |
| Predicate | performedBackingVocalsFor |
P28444
|
FINISHED |
| Object | Stevie Wonder recordings |
—
|
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: Stevie Wonder recordings | Statement: [Lynda Laurence, performedBackingVocalsFor, Stevie Wonder recordings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedBackingVocalsFor Context triple: [Lynda Laurence, performedBackingVocalsFor, Stevie Wonder recordings]
-
A.
hasBackingVocals
chosen
Indicates that one musical performance, track, or part includes supporting vocal contributions accompanying a primary vocal line.
-
B.
performedSongFor
Indicates that one entity performed a song specifically for another entity as the intended audience or recipient.
-
C.
hasVocalPerformanceBy
Indicates that a vocal performance in a work or recording is performed by a specified person or group.
-
D.
hasBackwardVocals
Indicates that the subject uses or contains backward (reversed) vocal audio in relation to the object.
-
E.
performedAsSingerIn
Indicates that an entity took part in a performance specifically in the role of a singer within a particular event, production, or context.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:52 p.m.