Triple
T3791806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morzine |
E89667
|
entity |
| Predicate | hasRoadAccessTo |
P22549
|
FINISHED |
| Object | Avoriaz |
E430186
|
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: Avoriaz | Statement: [Morzine, hasRoadAccessTo, Avoriaz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avoriaz Context triple: [Morzine, hasRoadAccessTo, Avoriaz]
-
A.
Avoriaz
chosen
Avoriaz is a purpose-built, car-free ski resort in the French Alps, known for its modern architecture and central position in the vast Portes du Soleil ski area.
-
B.
Tignes
Tignes is a high-altitude ski resort and alpine commune in the French Alps, renowned for its extensive ski area and year-round glacier skiing.
-
C.
La Clusaz
La Clusaz is a well-known French Alpine village and ski resort renowned for its extensive slopes and traditional mountain charm.
-
D.
La Plagne
La Plagne is a major French Alpine ski resort renowned for its extensive slopes and role as a venue during the 1992 Albertville Winter Olympics.
-
E.
Val-d’Isère
Val-d’Isère is a renowned French Alpine ski resort village famous for its extensive slopes and role as a host venue for major international skiing competitions.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee7687c4481908d5e6988e2638b68 |
completed | March 9, 2026, 3:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e4ca9164819088b261d148e0d379 |
completed | March 14, 2026, 10:44 p.m. |
Created at: March 9, 2026, 3:15 p.m.