Triple

T16155478
Position Surface form Disambiguated ID Type / Status
Subject University Library of KU Leuven E392028 entity
Predicate isLandmarkOf P6629 FINISHED
Object Leuven E78057 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: Leuven | Statement: [University Library of KU Leuven, isLandmarkOf, Leuven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leuven
Context triple: [University Library of KU Leuven, isLandmarkOf, Leuven]
  • A. Leuven chosen
    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.
  • B. 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.
  • C. Mechelen
    Mechelen is a historic city in the Flemish region of Belgium, known for its rich architectural heritage, medieval center, and prominent role in the Low Countries’ political and religious history.
  • D. Tervuren
    Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
  • E. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e5902a08190ad8694955ef6073a completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00aae0f87c819085ebc7d475ebe8ba completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:01 a.m.