Triple

T5468325
Position Surface form Disambiguated ID Type / Status
Subject University of Liège E122768 entity
Predicate locatedIn P40 FINISHED
Object Liège E142916 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: Liège | Statement: [University of Liège, locatedIn, Liège]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liège
Context triple: [University of Liège, locatedIn, Liège]
  • A. Liège chosen
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • B. Namur
    Namur is a historic Belgian city and the capital of Wallonia, located at the confluence of the Meuse and Sambre rivers.
  • C. Braine-l'Alleud
    Braine-l'Alleud is a municipality in Walloon Brabant, Belgium, known for encompassing much of the historic Waterloo battlefield.
  • D. Nivelles
    Nivelles is a historic town in present-day Belgium known for its medieval architecture, including the Romanesque Collegiate Church of Saint Gertrude.
  • E. Binche
    Binche is a historic town in the Walloon region of Belgium, renowned for its well-preserved medieval architecture and its UNESCO-recognized Carnival of Binche.
  • 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_69bd4643f16081908d7f29e08096115a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd92198ea08190a08357f3756572a2 completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d4f458288190ac1d6a8489bbc943 completed March 27, 2026, 7:05 p.m.
Created at: March 20, 2026, 2:09 p.m.