Triple
T3107697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savoie |
E64871
|
entity |
| Predicate | wineRegion |
P6176
|
FINISHED |
| Object | Vin de Savoie |
E64871
|
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: Vin de Savoie | Statement: [Savoie, wineRegion, Vin de Savoie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vin de Savoie Context triple: [Savoie, wineRegion, Vin de Savoie]
-
A.
Savoie
chosen
Savoie is a mountainous department in southeastern France, known for its Alpine landscapes, ski resorts, and rich Savoyard cultural heritage.
-
B.
Riviera vaudoise
Riviera vaudoise is a picturesque region along the northeastern shore of Lake Geneva in the canton of Vaud, Switzerland, known for its vineyards, lakeside towns, and mild microclimate.
-
C.
Drôme
Drôme is a department in southeastern France known for its diverse landscapes, historic towns, and location between the Alps and the Rhône Valley.
-
D.
Mâconnais
Mâconnais is a wine-producing subregion in southern Burgundy, France, best known for its Chardonnay-based white wines.
-
E.
Haute-Savoie
Haute-Savoie is a department in the Auvergne-Rhône-Alpes region of southeastern France, renowned for its Alpine landscapes, ski resorts, and proximity to Mont Blanc and the Swiss and Italian borders.
- 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_69ad857eeaf48190b34ebfdaa7a264cf |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada29d4aa8819093287bc71370fc05 |
completed | March 8, 2026, 4:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20f5994088190abc4b56040922c16 |
completed | March 12, 2026, 12:56 a.m. |
Created at: March 8, 2026, 3:04 p.m.