Triple
T18358913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sweet Talkin' Woman |
E439864
|
entity |
| Predicate | performer |
P1363
|
FINISHED |
| Object | Bev Bevan |
—
|
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: Bev Bevan | Statement: [Sweet Talkin' Woman, performer, Bev Bevan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bev Bevan Context triple: [Sweet Talkin' Woman, performer, Bev Bevan]
-
A.
Bev Bevan
chosen
Bev Bevan is an English rock drummer best known as a founding member of the Electric Light Orchestra and former member of The Move.
-
B.
Anthony Bevan
Anthony Bevan was a British orientalist and scholar of Semitic languages known for his contributions to the study of Arabic and Hebrew texts.
-
C.
Norman Bevan
Norman Bevan was a sports executive best known for owning the short-lived World Football League team, the San Antonio Wings, in the mid-1970s.
-
D.
Bill Bellamy
Bill Bellamy is an American stand-up comedian and actor known for his work on MTV in the 1990s and roles in films like "How to Be a Player" and "Love Jones."
-
E.
Ed Bevan
Ed Bevan is an individual notable enough to be recognized as a prominent bearer of the surname Bevan.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d9dba8819088c5d772e3ee670d |
completed | April 19, 2026, 5:54 p.m. |
Created at: April 10, 2026, 10:37 a.m.