Triple
T15761152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vézère Valley |
E382098
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Saint-Léon-sur-Vézère |
E321789
|
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: Saint-Léon-sur-Vézère | Statement: [Vézère Valley, contains, Saint-Léon-sur-Vézère]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Léon-sur-Vézère Context triple: [Vézère Valley, contains, Saint-Léon-sur-Vézère]
-
A.
Villeneuve-sur-Lot
Villeneuve-sur-Lot is a historic market town in southwestern France known for its medieval architecture and scenic riverside setting.
-
B.
Montignac
Montignac is a small town in southwestern France best known as the gateway to the prehistoric Lascaux cave complex.
-
C.
Vézac
chosen
Vézac is a small French commune, best known for its picturesque Dordogne Valley setting and historic gardens such as the Jardins de Marqueyssac.
-
D.
Caudéran
Caudéran is a residential district in the western part of Bordeaux, France, known for its parks and suburban character.
-
E.
Montsaunès
Montsaunès is a small commune in southwestern France, located in the Haute-Garonne department in the Occitanie region.
- 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_69d86d9e6b44819085d1f6a969ecb74c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e050b52c548190a0ffa4493a4eb15c |
completed | April 16, 2026, 3 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff8774eda08190a6231b4fd5027e6f |
completed | May 9, 2026, 7:13 p.m. |
Created at: April 10, 2026, 4:47 a.m.