Triple
T10066667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Set Fire to the Rain |
E213118
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Fraser T. Smith |
E848359
|
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: Fraser T. Smith | Statement: [Set Fire to the Rain, writer, Fraser T. Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fraser T. Smith Context triple: [Set Fire to the Rain, writer, Fraser T. Smith]
-
A.
Fraser T. Smith
chosen
Fraser T. Smith is a British record producer, songwriter, and musician known for his work with prominent artists across hip hop, grime, and pop, including collaborations with Adele, Stormzy, and Dave.
-
B.
Richard D. Smith
Richard D. Smith is a theatrical producer known for his work on the hit Broadway musical "The Producers."
-
C.
Richard W. Smith
Richard W. Smith is a member of the Smith family best known as a son of FedEx founder Frederick W. Smith.
-
D.
Douglas J. Foskett
Douglas J. Foskett was a British librarian and information scientist known for his influential work in library classification and information retrieval.
-
E.
Rodney D. Smith
Rodney D. Smith is an academic leader who has served as president of the University of The Bahamas.
- 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_69ca83977128819084084eb7d1d8c52a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcff63a4c8190bb08a0428aafa189 |
completed | April 2, 2026, 2:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a8c95ca081908ceaa89eef87fbc9 |
completed | April 18, 2026, 3:52 p.m. |
Created at: March 30, 2026, 8:58 p.m.