Triple
T10323029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Esther Kahn |
E242687
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Arnaud Desplechin |
E667165
|
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: Arnaud Desplechin | Statement: [Esther Kahn, director, Arnaud Desplechin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arnaud Desplechin Context triple: [Esther Kahn, director, Arnaud Desplechin]
-
A.
Arnaud Desplechin
chosen
Arnaud Desplechin is a French film director and screenwriter known for his complex, character-driven dramas such as "Kings and Queen" and "A Christmas Tale."
-
B.
Bertrand Tavernier
Bertrand Tavernier was a renowned French filmmaker and screenwriter known for his humanistic, socially engaged dramas and significant contributions to post–New Wave French cinema.
-
C.
Jacques Audiard
Jacques Audiard is an acclaimed French film director and screenwriter known for intense, character-driven dramas such as "A Prophet" and "Dheepan."
-
D.
Benoît Jacquot
Benoît Jacquot is a French film director known for his psychologically nuanced, often literary adaptations and intimate character studies.
-
E.
Olivier Assayas
Olivier Assayas is a French film director and screenwriter known for his eclectic, character-driven works that blend art-house sensibilities with genre elements.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d6cdb6cc8190b37ca4494287128b |
completed | April 7, 2026, 10:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94aec37288190bd9060ba39ec4df2 |
completed | April 10, 2026, 7:09 p.m. |
Created at: April 6, 2026, 11:50 a.m.