Triple
T22689737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maurice Jarre |
E561017
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | France Pejot |
—
|
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: France Pejot | Statement: [Maurice Jarre, spouse, France Pejot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: France Pejot Context triple: [Maurice Jarre, spouse, France Pejot]
-
A.
France Pejot
chosen
France Pejot was the wife of renowned French composer Maurice Jarre.
-
B.
Anne Pigalle
Anne Pigalle is a French-born chanteuse, visual artist, and performer known for her avant-garde style and work in the 1980s London art and music scene.
-
C.
Josette du Pres
Josette du Pres is a tragic, ghostly heroine from the gothic soap opera "Dark Shadows," remembered as the great love of vampire Barnabas Collins.
-
D.
Pauline Kergomard
Pauline Kergomard was a pioneering French educator and inspector of nursery schools, renowned for her influential reforms in early childhood education.
-
E.
Germaine Aussey
Germaine Aussey was a French film actress active in the 1930s and 1940s, known for her roles in comedies and popular European cinema of the era.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789a1fd08190bce5fa0babe695d3 |
completed | April 29, 2026, 3:18 a.m. |
Created at: April 17, 2026, 3:13 p.m.