Triple

T21305338
Position Surface form Disambiguated ID Type / Status
Subject Byres Road E525182 entity
Predicate near P350 FINISHED
Object Kelvin Hall 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: Kelvin Hall | Statement: [Byres Road, near, Kelvin Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelvin Hall
Context triple: [Byres Road, near, Kelvin Hall]
  • A. Kelvin Hall chosen
    Kelvin Hall is a historic sports, exhibition, and cultural venue in Glasgow, Scotland, known for hosting events and housing museum and leisure facilities.
  • B. Kelvin Grove campus
    Kelvin Grove campus is a major inner-city campus of the Queensland University of Technology in Brisbane, known for its creative industries, health, and education facilities.
  • C. Birkenhead Institute
    Birkenhead Institute was a former secondary school in Birkenhead, England, best known for educating the renowned First World War poet Wilfred Owen.
  • D. King’s Buildings
    King’s Buildings is the University of Edinburgh’s main science and engineering campus, housing many of its research institutes, laboratories, and related teaching facilities.
  • E. Wilf Hall
    Wilf Hall is an academic building at New York University School of Law that houses classrooms, faculty offices, and legal program facilities.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75aa3f90481909b212bdbf00c2bb0 completed April 21, 2026, 11:08 a.m.
Created at: April 16, 2026, 4:05 p.m.