Triple
T20872743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Round Midnight (film) |
E513934
|
entity |
| Predicate | starred |
P5563
|
FINISHED |
| Object | François Cluzet |
—
|
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: François Cluzet | Statement: [Round Midnight (film), starred, François Cluzet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: François Cluzet Context triple: [Round Midnight (film), starred, François Cluzet]
-
A.
François Cluzet
chosen
François Cluzet is a French actor acclaimed for his versatile performances in film and television, notably in the hit drama "The Intouchables."
-
B.
Jean-Luc Ourgaud
Jean-Luc Ourgaud is a French local politician who serves as the mayor of the suburban commune of Montigny-le-Bretonneux, near Paris.
-
C.
Michel Bouquet
Michel Bouquet was a renowned French actor celebrated for his nuanced performances in theatre and film over a career spanning more than six decades.
-
D.
François Durif
François Durif was a French grape breeder best known for creating the Petite Sirah (Durif) wine grape variety in the 19th century.
-
E.
Jean-Claude Olivier
Jean-Claude Olivier is a music producer best known for his work on George Michael’s landmark album "Faith."
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c465693881909fe4c756ddc4f291 |
completed | April 21, 2026, 12:27 a.m. |
Created at: April 16, 2026, 12:45 p.m.