Triple
T23362347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mon homme |
E593216
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Aurore Clément |
—
|
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: Aurore Clément | Statement: [Mon homme, castMember, Aurore Clément]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aurore Clément Context triple: [Mon homme, castMember, Aurore Clément]
-
A.
Aurore Clément
chosen
Aurore Clément is a French actress known for her work in European art cinema and international films, often collaborating with acclaimed directors such as Wim Wenders and Francis Ford Coppola.
-
B.
Tiphaine Auzière
Tiphaine Auzière is a French lawyer and political figure known both for her legal career and as the daughter of France’s First Lady, Brigitte Macron.
-
C.
Clémence Guichard
Clémence Guichard is a French actress and model best known by her stage name Clémence Poésy, recognized for roles in films like the Harry Potter series and In Bruges.
-
D.
Aurore Pajot
Aurore Pajot is known as the spouse of acclaimed French film director Claude Chabrol.
-
E.
Aurélie Charillon
Aurélie Charillon is a French local politician serving as the mayor of the commune of Prévessin-Moëns in eastern France.
- 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aa0ed88190b0198cbfd1bcc59b |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:30 p.m.