Triple

T18219745
Position Surface form Disambiguated ID Type / Status
Subject Bouillon Castle E436261 entity
Predicate locatedIn P40 FINISHED
Object Bouillon 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: Bouillon | Statement: [Bouillon Castle, locatedIn, Bouillon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bouillon
Context triple: [Bouillon Castle, locatedIn, Bouillon]
  • A. Bouillon chosen
    Bouillon is a historic town in southern Belgium’s Ardennes region, best known for its medieval castle overlooking the Semois River and its association with Crusader leader Godfrey of Bouillon.
  • B. La Boisse
    La Boisse is a commune in the Ain department of eastern France, situated in the Auvergne-Rhône-Alpes region.
  • C. Bouch
    Bouch is a surname most notably associated with Sir Thomas Bouch, a 19th-century British railway engineer involved in the design of the ill-fated original Tay Bridge.
  • D. Bessan
    Bessan is a commune in southern France, known for its historic village center and wine-producing countryside in the Hérault department.
  • E. Samoussy
    Samoussy is a commune in northern France, historically noted as the place where the Frankish king Carloman I died.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47a3b1c8190919e954089b41ae0 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.