Triple
T23326768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chemistry |
E591313
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Linda Creed |
—
|
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: Linda Creed | Statement: [Chemistry, producer, Linda Creed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Linda Creed Context triple: [Chemistry, producer, Linda Creed]
-
A.
Linda Creed
chosen
Linda Creed was an American songwriter best known for penning numerous soul and R&B hits in the 1970s and 1980s, often in collaboration with producer Thom Bell.
-
B.
Eileen Creed
Eileen Creed is an individual whose full name corresponds to the person known as Ellie Creed.
-
C.
Lynette Paradise
Lynette Paradise is an American podcast host and media personality best known as the wife of comedian and broadcaster Adam Carolla and co-host of the parenting podcast "For Crying Out Loud."
-
D.
Arlene Donovan
Arlene Donovan is a film producer best known for her work on the acclaimed 1984 drama "Places in the Heart."
-
E.
Lynette Curran
Lynette Curran is an Australian actress known for her extensive work in film, television, and theatre since the 1960s.
- 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f197eaa7b88190aad2096c110dadea |
completed | April 29, 2026, 5:32 a.m. |
Created at: April 17, 2026, 5:12 p.m.