Triple

T15812555
Position Surface form Disambiguated ID Type / Status
Subject Flemish Ardennes E383389 entity
Predicate contains P35 FINISHED
Object Kluisberg E1177863 NE FINISHED

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: Kluisberg | Statement: [Flemish Ardennes, contains, Kluisberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kluisberg
Context triple: [Flemish Ardennes, contains, Kluisberg]
  • A. Kruisberg chosen
    Kruisberg is a well-known climb in the Flemish Ardennes, frequently featured in Belgian professional cycling races.
  • B. De Vliedberg
    De Vliedberg is a residential neighborhood located within the Dutch municipality of Hellevoetsluis in South Holland.
  • C. Vaalserberg
    Vaalserberg is a hill in the southeastern Netherlands known as the country's highest point and the location of the tripoint where the borders of the Netherlands, Germany, and Belgium meet.
  • D. Zandbergen
    Zandbergen is a village in East Flanders, Belgium, that forms part of the municipality of Geraardsbergen.
  • E. Kortenberg
    Kortenberg is a municipality in the Flemish Brabant province of Belgium, located between Brussels and Leuven and known for its residential character and green surroundings.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da2858c819090cc8481e7207b6e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0c4a069bc8190bf9504dc6c998fa2 completed April 16, 2026, 11:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffa131784c8190bd6aba2cca084d20 completed May 9, 2026, 9:03 p.m.
Created at: April 10, 2026, 4:49 a.m.