Triple

T19776956
Position Surface form Disambiguated ID Type / Status
Subject Arrondissement of Soissons E475026 entity
Predicate administrativeCenter P1474 FINISHED
Object Soissons 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: Soissons | Statement: [Arrondissement of Soissons, administrativeCenter, Soissons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soissons
Context triple: [Arrondissement of Soissons, administrativeCenter, Soissons]
  • A. Soissons chosen
    Soissons is a historic town in northern France known for its strategic military importance and notable battles throughout European history.
  • B. Poissy
    Poissy is a commune in the western suburbs of Paris, France, known for hosting Le Corbusier’s iconic modernist Villa Savoye.
  • C. Essonnes
    Essonnes was a former commune in northern France that later became part of the town of Corbeil-Essonnes in the Île-de-France region.
  • D. Dourdan
    Dourdan is a commune in the Essonne department in the southern suburbs of Paris, France, known for its historic medieval castle and role as a terminus on the RER C suburban rail line.
  • E. Château-Thierry
    Château-Thierry is a historic town in northern France known for its World War I battlefields and its association with the poet Jean de La Fontaine.
  • 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65360cca08190957c36b1a440542c completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:48 p.m.