Triple

T783613
Position Surface form Disambiguated ID Type / Status
Subject Ghent University E16553 entity
Predicate locatedIn P40 FINISHED
Object Ghent E53969 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: Ghent | Statement: [Ghent University, locatedIn, Ghent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghent
Context triple: [Ghent University, locatedIn, Ghent]
  • A. Ghent chosen
    Ghent is a historic city in the Flemish region of Belgium, known for its medieval architecture, canals, and role as a major cultural and economic center in the Middle Ages.
  • B. Antwerp
    Antwerp is a major Belgian port city on the River Scheldt, renowned as a global center for the diamond trade and its historic Flemish art and architecture.
  • C. 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.
  • D. 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.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7686d0881908c2a4395059be02c completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac427da0348190a8ae16db2a048d0b completed March 7, 2026, 3:21 p.m.
Created at: March 1, 2026, 7:37 p.m.