Triple
T5577677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Didn’t Mean to Turn You On |
E146361
|
entity |
| Predicate | originallyPerformedBy |
P11499
|
FINISHED |
| Object | Cherrelle |
E536202
|
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: Cherrelle | Statement: [Didn’t Mean to Turn You On, originallyPerformedBy, Cherrelle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cherrelle Context triple: [Didn’t Mean to Turn You On, originallyPerformedBy, Cherrelle]
-
A.
Cherrelle
chosen
Cherrelle is an American R&B singer best known for her 1980s hits and collaborations with producers Jimmy Jam and Terry Lewis.
-
B.
Cherie
Cherie is the naive yet determined young woman who becomes the romantic focus of the cowboy in the classic stage play and film "Bus Stop."
-
C.
Charlene
Charlene is a feminine given name derived from the male name Charles.
-
D.
Michel'le
Michel'le is an American R&B singer known for her distinctive high-pitched speaking voice and late-1980s and early-1990s hits such as "No More Lies."
-
E.
Cordelle
Cordelle is a given name and surname, typically considered a variant of Cordell, used for both males and females.
- 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_69c008ffed108190a084602227af6157 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0206ae4808190971d89243db94475 |
completed | March 22, 2026, 5:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c059f3f6648190af2fd9a5e7cc125b |
completed | March 22, 2026, 9:07 p.m. |
Created at: March 22, 2026, 3:37 p.m.