Triple
T13753188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antoine Arnault |
E330405
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Anne Dewavrin |
E339967
|
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: Anne Dewavrin | Statement: [Antoine Arnault, parent, Anne Dewavrin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anne Dewavrin Context triple: [Antoine Arnault, parent, Anne Dewavrin]
-
A.
Anne Dewavrin
chosen
Anne Dewavrin is a French socialite known primarily for her past marriage to billionaire businessman Bernard Arnault, the chairman and CEO of LVMH.
-
B.
Corinne Jorry
Corinne Jorry is a French costume designer renowned for her work on period films and collaborations with prominent European directors.
-
C.
Catherine Fabienne Dorléac
Catherine Fabienne Dorléac is the birth name of Catherine Deneuve, the iconic French actress renowned for her roles in films such as "The Umbrellas of Cherbourg" and "Belle de Jour."
-
D.
Marianne Denicourt
Marianne Denicourt is a French actress known for her work in art-house and mainstream French cinema since the 1980s.
-
E.
Doriane Bécue
Doriane Bécue is a French politician who serves as the mayor of the city of Tourcoing in northern France.
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0215cfa08190aaed8b089aff217b |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c20e45c8190968a5d88a2b3fe37 |
completed | May 8, 2026, 2:36 a.m. |
Created at: April 9, 2026, 10:09 p.m.