Triple
T22466501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vĩnh Thụy |
E555368
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Monique Baudot |
—
|
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: Monique Baudot | Statement: [Vĩnh Thụy, spouse, Monique Baudot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Monique Baudot Context triple: [Vĩnh Thụy, spouse, Monique Baudot]
-
A.
Monique Baudot
chosen
Monique Baudot was the French-born second wife of Vietnam’s last emperor, Bảo Đại, known for her life in exile with him in France.
-
B.
Monique Bonnot
Monique Bonnot is a French film editor known for her work on numerous notable European films, including collaborations with prominent directors of the 1960s and 1970s.
-
C.
Monique Dartonne
Monique Dartonne is a film editor best known for her work on acclaimed films such as Denis Villeneuve’s "Incendies."
-
D.
Monique Teisseire
Monique Teisseire is a film editor best known for her work on the classic French musical drama "The Umbrellas of Cherbourg."
-
E.
Monique Nicolas
Monique Nicolas is best known as the wife of celebrated French singer-songwriter and pianist Gilbert Bécaud.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b837ec081909c4e44d37e8b2acd |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.