Triple
T1283671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vaucluse |
E27382
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Mont Ventoux |
E151739
|
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: Mont Ventoux | Statement: [Vaucluse, contains, Mont Ventoux]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont Ventoux Context triple: [Vaucluse, contains, Mont Ventoux]
-
A.
Mont Ventoux
chosen
Mont Ventoux is a prominent limestone mountain in Provence, France, famed for its barren, lunar-like summit and its frequent, challenging appearances in the Tour de France.
-
B.
Col du Dôme
Col du Dôme is a high mountain pass in the Mont Blanc massif of the French Alps, situated between major glaciated summits and commonly traversed on classic alpine climbing routes.
-
C.
Mont Aigoual
Mont Aigoual is a prominent peak in the Cévennes range of southern France, known for its panoramic views and historic meteorological observatory.
-
D.
Col de l’Échelle
Col de l’Échelle is a high mountain pass in the Alps that provides a key road link between France and Italy.
-
E.
Col du Mont Maudit
Col du Mont Maudit is a high mountain pass in the Mont Blanc massif of the Alps, used by alpinists as part of classic routes across the glaciated terrain between France and Italy.
- 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_69a496d3710c8190955dee8bc0dacb50 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c0b599ac819096fca9ada294d939 |
completed | March 1, 2026, 10:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad231d1bdc8190bceaafcf86544bf1 |
completed | March 8, 2026, 7:19 a.m. |
Created at: March 1, 2026, 7:50 p.m.