Triple
T22925302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guil |
E569287
|
entity |
| Predicate | mouthNear |
P18935
|
FINISHED |
| Object | Mont-Dauphin |
—
|
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: Mont-Dauphin | Statement: [Guil, mouthNear, Mont-Dauphin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont-Dauphin Context triple: [Guil, mouthNear, Mont-Dauphin]
-
A.
Mont-Dauphin
chosen
Mont-Dauphin is a fortified village in southeastern France, renowned for its 17th-century Vauban-designed defenses and strategic position overlooking the confluence of Alpine valleys.
-
B.
Saint-François
Saint-François is a district of Laval, Quebec, known as a suburban residential area on Île Jésus northeast of Montreal.
-
C.
Saint-François
Saint-François is a coastal commune and popular tourist resort town located on the island of Grande-Terre in Guadeloupe, known for its marina, beaches, and proximity to Pointe des Châteaux.
-
D.
Duchesne
Duchesne refers to Antoine Nicolas Duchesne, an 18th-century French botanist and horticulturist known for his pioneering work on strawberries and other cultivated plants.
-
E.
Tignes le Lac
Tignes le Lac is a lakeside village and ski resort area in the French Alps, forming one of the main hubs of the broader Tignes ski domain.
- 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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d84fc08190b747c3f9052c657a |
completed | April 29, 2026, 3:54 a.m. |
Created at: April 17, 2026, 3:43 p.m.