Triple
T18834358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicolas de Staël |
E460617
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jeannine Guillou |
—
|
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: Jeannine Guillou | Statement: [Nicolas de Staël, spouse, Jeannine Guillou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeannine Guillou Context triple: [Nicolas de Staël, spouse, Jeannine Guillou]
-
A.
Jeannine Guillou
chosen
Jeannine Guillou was a French painter and the first wife and close artistic companion of the Russian-born French artist Nicolas de Staël.
-
B.
Jeannine Roussel
Jeannine Roussel is a film producer best known for her work on Disney’s animated sequel "The Lion King II: Simba’s Pride."
-
C.
Carole Grelaud
Carole Grelaud is a French local politician serving as the mayor of the commune of Couëron in western France.
-
D.
Sylviane Alaux
Sylviane Alaux is a French politician known for her involvement in centrist and independent political movements.
-
E.
Jacqueline Broyer
Jacqueline Broyer is a confident, high-powered executive and one of the central love interests in the romantic comedy film "Boomerang" (1992).
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99c1394819095c62eef040e552c |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.