Triple

T22687247
Position Surface form Disambiguated ID Type / Status
Subject Newhaven E560948 entity
Predicate hasFeature P182 FINISHED
Object Newhaven 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: Newhaven College | Statement: [Newhaven, hasFeature, Newhaven College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Newhaven College
Context triple: [Newhaven, hasFeature, Newhaven College]
  • A. Newhaven College chosen
    Newhaven College is an Australian secondary school best known for being attended by actor Liam Hemsworth.
  • B. Sackville College
    Sackville College is a historic almshouse and architectural landmark in East Grinstead, England, known for its well-preserved Jacobean buildings and charitable heritage.
  • C. Emmanuel College
    Emmanuel College is a private Roman Catholic liberal arts college located in Boston, Massachusetts.
  • D. Christ Church College
    Christ Church College is one of the largest and most prestigious colleges of the University of Oxford, renowned for its grand architecture, historic cathedral, and appearances in popular culture such as the Harry Potter films.
  • E. Penfield College
    Penfield College is an academic division of Mercer University that focuses on undergraduate liberal arts and professional studies.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178649aac8190a9d41f5d82895bdf completed April 29, 2026, 3:17 a.m.
Created at: April 17, 2026, 3:13 p.m.