Triple

T2725510
Position Surface form Disambiguated ID Type / Status
Subject LERU E60180 entity
Predicate headquartersLocation P62 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: [LERU, headquartersLocation, Leuven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leuven
Context triple: [LERU, headquartersLocation, 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. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • 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 (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_69ab4b746d248190958e052045c09255 completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdacd7e24819084a620063e3f7aa4 completed March 7, 2026, 7:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69b4fad35a0c8190a07cc7877fbfec04 completed March 14, 2026, 6:06 a.m.
Created at: March 6, 2026, 9:55 p.m.