Triple
T22579002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bitter Sweet |
E544514
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Tony Silvester |
—
|
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: Tony Silvester | Statement: [Bitter Sweet, producer, Tony Silvester]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Silvester Context triple: [Bitter Sweet, producer, Tony Silvester]
-
A.
Tony Silvester
chosen
Tony Silvester was an American soul singer best known as a founding member and vocalist of the R&B group The Main Ingredient.
-
B.
Ronald Bateman
Ronald Bateman is best known as the husband of British novelist and playwright Fay Weldon.
-
C.
Victor Silvester
Victor Silvester was a renowned British ballroom dancer, bandleader, and composer who popularized strict-tempo dance music in the mid-20th century.
-
D.
Tony Worthington
Tony Worthington is a notable individual who shares the surname Worthington and has achieved sufficient prominence to be specifically recognized by name.
-
E.
Tony Maudsley
Tony Maudsley is a British actor best known for his comedic television roles, including his long-running part as Kenneth in the sitcom "Benidorm."
- 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_69e11e30d05481909df915354c89f0d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f15feee27c8190b31c923e1f00a363 |
completed | April 29, 2026, 1:33 a.m. |
Created at: April 16, 2026, 8:53 p.m.