Triple
T18252965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Convoyeur |
E437144
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | François Berléand |
—
|
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 Berléand | Statement: [Le Convoyeur, stars, François Berléand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: François Berléand Context triple: [Le Convoyeur, stars, François Berléand]
-
A.
François Berléand
chosen
François Berléand is a French character actor known for his prolific film and television career, often portraying authoritative or world-weary figures in dramas and thrillers.
-
B.
François Lecointre
François Lecointre is a French Army general who served as France’s Chief of the Defence Staff.
-
C.
Éric Neveux
Éric Neveux is a French film and television composer known for his atmospheric and emotionally nuanced scores.
-
D.
Didier Auriol
Didier Auriol is a French rally driver and 1994 World Rally Champion, renowned for his success in the World Rally Championship during the late 1980s and 1990s.
-
E.
Christophe Lourdelet
Christophe Lourdelet is a French animator and film director known for his work on major animated features, including co-directing the musical comedy film "Sing 2."
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4fd81ea3481909d96b5399f7a32b3 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 10:33 a.m.