Triple

T5570121
Position Surface form Disambiguated ID Type / Status
Subject Albert Canal E145976 entity
Predicate locatedNear P294 FINISHED
Object Hasselt E165235 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: Hasselt | Statement: [Albert Canal, locatedNear, Hasselt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hasselt
Context triple: [Albert Canal, locatedNear, Hasselt]
  • A. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • B. Hasselt chosen
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • C. Vilvoorde
    Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
  • D. Aalst
    Aalst is a historic city in the Belgian province of East Flanders, known for its textile industry and famous annual carnival.
  • E. Leuven
    Leuven is a historic Belgian city known for hosting KU Leuven, one of Europe’s leading research universities, and for its vibrant academic and cultural life.
  • 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_69c008fdae24819081aa002ad99cd966 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0204f0d288190b9d4884665ba9116 completed March 22, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6e3ff314c8190b66f8b0a7ae3c039 completed March 27, 2026, 8:09 p.m.
Created at: March 22, 2026, 3:36 p.m.