Triple

T23295965
Position Surface form Disambiguated ID Type / Status
Subject Bishop of Digne E590170 entity
Predicate fictionalLocation P18263 FINISHED
Object Digne 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: Digne | Statement: [Bishop of Digne, fictionalLocation, Digne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Digne
Context triple: [Bishop of Digne, fictionalLocation, Digne]
  • A. Digne-les-Bains chosen
    Digne-les-Bains is a spa town in southeastern France that serves as the administrative and cultural center of the Alpes-de-Haute-Provence department.
  • B. Saint-Just-d’Ardèche
    Saint-Just-d’Ardèche is a small commune in the Ardèche department of southern France, known for its scenic location along the Rhône River and proximity to the Ardèche Gorges.
  • C. Valréas
    Valréas is a historic town in southeastern France known for its wine production and its former status as an exclave of the Papal Comtat Venaissin.
  • D. Cavaillon
    Cavaillon is a town in southeastern France’s Vaucluse department, known for its melon production and location at the foot of the Luberon massif.
  • E. Couzeix
    Couzeix is a commune in west-central France, located in the Haute-Vienne department of the Nouvelle-Aquitaine region near the city of Limoges.
  • 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_69e25d1af9d88190a0b9b5e8fa608618 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196cec9e88190b83cfd53a6455e0f completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.