Triple
T3656982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-André-du-Bois |
E77555
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Gironde |
E225917
|
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: Gironde | Statement: [Saint-André-du-Bois, locatedIn, Gironde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gironde Context triple: [Saint-André-du-Bois, locatedIn, Gironde]
-
A.
Gironde
chosen
Gironde is a department in southwestern France that encompasses much of the Bordeaux wine region, including renowned appellations such as Graves.
-
B.
Charente
Charente is a department in southwestern France known for its historic towns, cognac production, and scenic river landscapes.
-
C.
Dordogne
Dordogne is a major river in southwestern France known for flowing through the Dordogne valley, a region famed for its picturesque landscapes, historic towns, and prehistoric cave art.
-
D.
Haute-Vienne
Haute-Vienne is a department in west-central France, within the Nouvelle-Aquitaine region, known for its capital Limoges and its historic porcelain industry.
-
E.
Aveyron
Aveyron is a rural department in southern France known for its rugged landscapes, medieval villages, and traditional gastronomy including Roquefort cheese.
- 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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3d36c1c8190920397a75de4c47d |
completed | March 8, 2026, 6:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4883dc5408190a6e7e110acf03a15 |
completed | March 13, 2026, 9:57 p.m. |
Created at: March 8, 2026, 3:24 p.m.