Triple

T17424552
Position Surface form Disambiguated ID Type / Status
Subject Curan E423703 entity
Predicate nearbyCity P350 FINISHED
Object Millau 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: Millau | Statement: [Curan, nearbyCity, Millau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millau
Context triple: [Curan, nearbyCity, Millau]
  • A. Millau chosen
    Millau is a town in southern France best known for the nearby Millau Viaduct, one of the world’s tallest and most spectacular cable-stayed bridges.
  • B. Pont-Saint-Esprit
    Pont-Saint-Esprit is a historic commune in southern France, known for its medieval bridge over the Rhône River and its location in the Gard department of the Occitanie region.
  • C. Manosque
    Manosque is a historic town in southeastern France’s Provence region, known for its medieval old town, surrounding lavender fields, and proximity to the Luberon mountains.
  • D. Gradignan
    Gradignan is a suburban commune in southwestern France’s Gironde department, forming part of the Bordeaux metropolitan area and known for its green spaces and wine-growing surroundings.
  • E. Rochechouart
    Rochechouart is a small historic town in west-central France known for its medieval château and proximity to the Rochechouart impact crater site.
  • 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4423999ac81909fdbd8bcffcb30c9 completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.