Triple
T22562664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friday (1995 film) |
E557856
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Patricia Charbonnet |
—
|
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: Patricia Charbonnet | Statement: [Friday (1995 film), producer, Patricia Charbonnet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patricia Charbonnet Context triple: [Friday (1995 film), producer, Patricia Charbonnet]
-
A.
Patricia Charbonnet
chosen
Patricia Charbonnet is a film producer best known for her work on the influential 1995 comedy "Friday."
-
B.
Patricia Blanchet
Patricia Blanchet is the widow of renowned American broadcast journalist Ed Bradley, known for her connection to his legacy in television news.
-
C.
Paulette Morisset
Paulette Morisset is known primarily as the daughter of André Morisset.
-
D.
Brigitte Bourgeois
Brigitte Bourgeois is a Canadian politician who served as a member of the National Assembly of Quebec.
-
E.
Nancy Dussault
Nancy Dussault is an American actress and singer best known for her work on Broadway and in television sitcoms, including the series "Too Close for Comfort."
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fa6a928819083925ea23aaaf725 |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.