Triple
T5998537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yves Cordonnier |
E133535
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cordonnier |
E133535
|
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: Cordonnier | Statement: [Yves Cordonnier, familyName, Cordonnier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cordonnier Context triple: [Yves Cordonnier, familyName, Cordonnier]
-
A.
Cordonnier
chosen
Cordonnier is a French surname most notably associated with Louis Marie Cordonnier, a prominent architect known for his influential work in northern France around the turn of the 20th century.
-
B.
Labouret
Labouret is a French surname associated with individuals such as Marie-Louise Élisabeth Labouret.
-
C.
Marchand
Marchand is the surname of American rapper and actress Foxy Brown, whose full name is Inga DeCarlo Fung Marchand.
-
D.
Boutes
Boutes is a minor figure in Greek mythology, traditionally regarded as a hero or priest associated with the Athenian royal house and the cult practices on the Acropolis.
-
E.
Meunier
Meunier is a common French occupational surname, historically referring to a miller.
- 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_69c00870ddbc81909880fa3864f4f38d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04ee49b708190a92c3fd1336e8ab0 |
completed | March 22, 2026, 8:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11cdec5608190ad093a09acd32ebf |
completed | March 23, 2026, 10:58 a.m. |
Created at: March 22, 2026, 4:05 p.m.