Triple
T16099492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rave On |
E390577
|
entity |
| Predicate | originalArtist |
P11499
|
FINISHED |
| Object | Sonny West |
E1194604
|
NE 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: Sonny West | Statement: [Rave On, originalArtist, Sonny West]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonny West Context triple: [Rave On, originalArtist, Sonny West]
-
A.
Sonny West
chosen
Sonny West was an American rockabilly singer-songwriter best known for co-writing early rock and roll classics later popularized by Buddy Holly.
-
B.
Sonny John Moore
Sonny John Moore is an American electronic music producer, DJ, and singer best known by his stage name Skrillex, a pioneering figure in modern dubstep and EDM.
-
C.
Brian West
Brian West is an author associated with the work "Força," contributing to its written content or storyline.
-
D.
Brian West
Brian West is a cinematographer best known for his work on the Canadian film "The Apprenticeship of Duddy Kravitz."
-
E.
Sonny Osborne
Sonny Osborne was an influential American bluegrass banjo player best known for his innovative work and harmonies with the Osborne Brothers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6672848190922b5ebb90e18947 |
completed | April 17, 2026, 9:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff29f9f2881909b96860ee23d8ada |
completed | May 10, 2026, 2:51 a.m. |
Created at: April 10, 2026, 5 a.m.