Triple

T16245275
Position Surface form Disambiguated ID Type / Status
Subject Sommières E394355 entity
Predicate locatedOnRiver P165 FINISHED
Object Vidourle E394356 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: Vidourle | Statement: [Sommières, locatedOnRiver, Vidourle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vidourle
Context triple: [Sommières, locatedOnRiver, Vidourle]
  • A. Vidourle chosen
    Vidourle is a river in southern France that flows through the Gard department before emptying into the Mediterranean Sea.
  • B. Alès
    Alès is a historic industrial town in southern France, located at the foot of the Cévennes mountains.
  • C. Ardiège
    Ardiège is a small commune in southwestern France, located in the Haute-Garonne department within the Occitanie region.
  • D. Vallée de la Roya
    Vallée de la Roya is a scenic river valley in the southern French Alps known for its dramatic gorges, historic hilltop villages, and role as a key route between France and Italy.
  • E. Vallée d’Aspe
    Vallée d’Aspe is a scenic valley in the French Pyrenees known for its mountainous landscapes, traditional villages, and role as a route through the western Pyrenean range.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24561d250819096f709ea8751fcb9 completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ee135b881909cc1b6919bc7af29 completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:04 a.m.