Triple

T13449404
Position Surface form Disambiguated ID Type / Status
Subject Howest University of Applied Sciences E320568 entity
Predicate hasCampus P116 FINISHED
Object Bruges campus E1040305 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: Bruges campus | Statement: [Howest University of Applied Sciences, hasCampus, Bruges campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bruges campus
Context triple: [Howest University of Applied Sciences, hasCampus, Bruges campus]
  • A. Brussels campus
    Brussels campus is the University of Kent’s postgraduate centre in Brussels, Belgium, focusing on international studies and related disciplines.
  • B. Kortrijk campus chosen
    Kortrijk campus is a main location of Howest University of Applied Sciences in Belgium, hosting a variety of practice-oriented higher education programs and student facilities.
  • C. Merelbeke campus
    Merelbeke campus is the Ghent University site that houses its Faculty of Veterinary Medicine and related teaching, research, and clinical facilities.
  • D. Ghent city campus
    Ghent city campus is an urban campus of Ghent University located in the city of Ghent, Belgium, hosting various academic faculties and facilities.
  • E. Solbosch campus
    Solbosch campus is the main and largest site of the Université libre de Bruxelles, hosting many of its central faculties, administrative buildings, and student facilities in Brussels.
  • 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_69d80761e6cc8190a90c844589998ecc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaef973b08190a3d7fe1c2a913cff completed April 12, 2026, 2:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7462340548190b156a8213f5e2556 completed May 3, 2026, 12:57 p.m.
Created at: April 9, 2026, 9:41 p.m.