Triple

T21371033
Position Surface form Disambiguated ID Type / Status
Subject Ieper E527061 entity
Predicate hasNativeName P1435 FINISHED
Object Ieper 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: Ieper | Statement: [Ieper, hasNativeName, Ieper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ieper
Context triple: [Ieper, hasNativeName, Ieper]
  • A. Ieper chosen
    Ieper is a historic Belgian city in West Flanders, best known for its World War I battlefields, memorials, and the nightly Last Post ceremony at the Menin Gate.
  • B. Aalst
    Aalst is a historic city in the Belgian province of East Flanders, known for its textile industry and famous annual carnival.
  • C. Luchteren
    Luchteren is a subdistrict or neighborhood within the Drongen area of Ghent in the Belgian province of East Flanders.
  • D. Torhout
    Torhout is a small city in West Flanders, Belgium, known for its educational institutions and its location near Bruges.
  • E. Hasselt
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • 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_69e0b51e80808190ba5cb05667af02a9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0ae92c88190a3d3097f5b268a79 completed April 22, 2026, 11:27 a.m.
Created at: April 16, 2026, 5:10 p.m.