Triple
T17340586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Story of Adèle H. |
E421054
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Yann Dedet |
—
|
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: Yann Dedet | Statement: [The Story of Adèle H., editedBy, Yann Dedet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yann Dedet Context triple: [The Story of Adèle H., editedBy, Yann Dedet]
-
A.
Yann Dedet
chosen
Yann Dedet is a French film editor renowned for his long-standing collaborations with prominent directors such as François Truffaut and Maurice Pialat.
-
B.
Yann Malcor
Yann Malcor is a film editor known for his work on the French psychological thriller "He Loves Me... He Loves Me Not."
-
C.
Laurent Vastel
Laurent Vastel is a French local politician who serves as the mayor of the Paris suburb Fontenay-aux-Roses.
-
D.
Yannick Vanderborght
Yannick Vanderborght is a Belgian political scientist best known for his work on basic income and social justice, often in collaboration with Philippe Van Parijs.
-
E.
Yannick Jauzion
Yannick Jauzion is a retired French rugby union centre renowned for his powerful running, playmaking skills, and key role in France’s national team during the 2000s.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a15f6488190ad7d489e7391ab12 |
completed | April 19, 2026, 2:12 a.m. |
Created at: April 10, 2026, 5:44 a.m.