Triple
T20766039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Académie Carrière |
E511098
|
entity |
| Predicate | notableStudent |
P4838
|
FINISHED |
| Object | Jean Puy |
—
|
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: Jean Puy | Statement: [Académie Carrière, notableStudent, Jean Puy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean Puy Context triple: [Académie Carrière, notableStudent, Jean Puy]
-
A.
Jean Puy
chosen
Jean Puy was a French Fauvist painter known for his vibrant use of color and participation in early 20th-century avant-garde exhibitions.
-
B.
Frémaux
Frémaux is a French surname most notably associated with Louis Frémaux, a prominent 20th-century conductor.
-
C.
Philippe Carcassonne
Philippe Carcassonne is a French film producer known for his work on acclaimed international features, including the 2020 drama "The Father."
-
D.
Saint Gilles
Saint Gilles is the French name for Saint Giles, a popular medieval Christian saint venerated as the patron of the disabled, beggars, and outcasts.
-
E.
Paul Gavarni
Paul Gavarni was a 19th-century French illustrator and caricaturist renowned for his satirical depictions of Parisian society.
- 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_69e0b4ca01148190ac018e57e0cab46f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c24ceab8819094e331c57abe6879 |
completed | April 21, 2026, 12:18 a.m. |
Created at: April 16, 2026, 12:36 p.m.