Triple
T17988451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col du Tourmalet |
E430301
|
entity |
| Predicate | hasNearbyVillage |
P4647
|
FINISHED |
| Object | Sainte-Marie-de-Campan |
—
|
NE NERFINISHED |
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: Sainte-Marie-de-Campan | Statement: [Col du Tourmalet, hasNearbyVillage, Sainte-Marie-de-Campan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sainte-Marie-de-Campan Context triple: [Col du Tourmalet, hasNearbyVillage, Sainte-Marie-de-Campan]
-
A.
Sainte-Marie-de-Campan
chosen
Sainte-Marie-de-Campan is a village in the French Pyrenees known as a traditional mountain gateway and cycling hub on classic Tour de France routes.
-
B.
Sainte-Marie-du-Mont
Sainte-Marie-du-Mont is a commune in Normandy, France, best known for its role in the D-Day landings as one of the first villages liberated by American forces.
-
C.
Saint-Martin-des-Plains
Saint-Martin-des-Plains is a small French commune located in the Puy-de-Dôme department in central France.
-
D.
Saint-Martin-le-Colonel
Saint-Martin-le-Colonel is a small commune in southeastern France, located in the Drôme department within the Auvergne-Rhône-Alpes region.
-
E.
Marly-la-Ville
Marly-la-Ville is a commune in the Val-d'Oise department in the northern suburbs of Paris, France.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b29d3ad4819096c2600aa2a99f21 |
completed | April 19, 2026, 10:46 a.m. |
Created at: April 10, 2026, 10:23 a.m.