Triple
T12486110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Café Guerbois |
E298436
|
entity |
| Predicate | frequentedBy |
P1097
|
FINISHED |
| Object | Nadar |
E296585
|
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: Nadar | Statement: [Café Guerbois, frequentedBy, Nadar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nadar Context triple: [Café Guerbois, frequentedBy, Nadar]
-
A.
Nadar
chosen
Nadar was a pioneering 19th-century French photographer, caricaturist, and balloonist known for his portraits of cultural figures and early use of aerial photography.
-
B.
Claude Lecomte
Claude Lecomte is a cinematographer known for his work on the French film "A Very Curious Girl."
-
C.
Marcel Lecomte
Marcel Lecomte was a Belgian writer and poet associated with the Surrealist movement in Brussels.
-
D.
Georges L. Dumont
Georges L. Dumont was a Canadian physician whose contributions to healthcare in New Brunswick led to a major francophone hospital in Moncton being named in his honor.
-
E.
Paul Moreau
Paul Moreau is a relatively obscure individual whose name is notably associated with the surname Moreau but who lacks widely documented public recognition.
- 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_69d6ada377208190a36011199a4d8558 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94de077bc81908b5ff057a1bf2b4f |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f2b5ed481909ead4f5b96d44064 |
completed | May 2, 2026, 6:15 p.m. |
Created at: April 8, 2026, 9:56 p.m.