Triple
T12972696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Combe de Savoie |
E321441
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Chambéry |
E46643
|
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: Chambéry | Statement: [Combe de Savoie, near, Chambéry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chambéry Context triple: [Combe de Savoie, near, Chambéry]
-
A.
Chambéry
chosen
Chambéry is a historic city in southeastern France that served as the political and cultural center of the former Duchy of Savoy.
-
B.
Grenoble
Grenoble is a major city in southeastern France, known for its Alpine setting, universities, and research centers.
-
C.
Aix-les-Bains
Aix-les-Bains is a French spa and resort town in the Savoie department, renowned for its thermal baths and lakeside setting on the edge of the Alps.
-
D.
Briançon
Briançon is a fortified alpine town in southeastern France, known as one of the highest cities in Europe and a key historical stronghold near the Italian border.
-
E.
Champéry
Champéry is a Swiss alpine village and ski resort in the canton of Valais, known for its access to the Portes du Soleil ski area and mountain tourism.
- 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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e418d548190be1c73db76cb3aa8 |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f77f74cb388190836484a1dd7d1d67 |
completed | May 3, 2026, 5:01 p.m. |
Created at: April 9, 2026, 8:36 p.m.