Triple

T22913355
Position Surface form Disambiguated ID Type / Status
Subject Randy Meeks E568659 entity
Predicate education P5 FINISHED
Object Windsor College 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: Windsor College | Statement: [Randy Meeks, education, Windsor College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Windsor College
Context triple: [Randy Meeks, education, Windsor College]
  • A. Windsor College chosen
    Windsor College is the fictional Ohio university where much of the action in the horror film "Scream 2" takes place.
  • B. Riverside College
    Riverside College is a further and higher education college based in Widnes, Cheshire, offering a range of vocational courses, A-levels, and adult learning programs.
  • C. Stephenson College
    Stephenson College is a constituent college of Durham University, providing accommodation, academic support, and a social community for its students.
  • D. Liston College
    Liston College is a Catholic boys' secondary school located in the suburb of Henderson in Auckland, New Zealand.
  • E. Selwyn College
    Selwyn College is a constituent college of the University of Cambridge in England, known for its red-brick Victorian architecture and strong academic and community ethos.
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1807668c481908494769bab9c8f1d completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.