Triple

T20772025
Position Surface form Disambiguated ID Type / Status
Subject Frankfurt–Brussels E511259 entity
Predicate viaStation P64719 FINISHED
Object Liège-Guillemins NE NERFINISHED

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-Guillemins | Statement: [Frankfurt–Brussels, viaStation, Liège-Guillemins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liège-Guillemins
Context triple: [Frankfurt–Brussels, viaStation, Liège-Guillemins]
  • A. Liège-Guillemins chosen
    Liège-Guillemins is a major high-speed railway station in Liège, Belgium, renowned for its striking modern architecture designed by Santiago Calatrava.
  • B. Royal Football Club de Liège
    Royal Football Club de Liège is a historic Belgian football club from the city of Liège, known as one of the country’s oldest and most traditional teams.
  • C. Anderlecht
    Anderlecht is a municipality in the Brussels-Capital Region of Belgium, known for its historic center and prominent football club R.S.C. Anderlecht.
  • D. RAEC Mons
    RAEC Mons is a Belgian professional football club based in Mons that has competed in the country’s top divisions.
  • E. Lierse
    Lierse refers to something or someone originating from or associated with the city of Lier in Belgium, commonly used as a demonym and in the names of local institutions such as sports clubs.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2681ff88190bfe5938c2db6b2c4 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.