Triple

T10635154
Position Surface form Disambiguated ID Type / Status
Subject College Street E250559 entity
Predicate near P350 FINISHED
Object Hare School E644226 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: Hare School | Statement: [College Street, near, Hare School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hare School
Context triple: [College Street, near, Hare School]
  • A. Hare School chosen
    Hare School is one of the oldest and most prestigious boys’ schools in Kolkata, India, known for its historical significance and contribution to modern education in Bengal.
  • B. Hayes School
    Hayes School is a co-educational secondary school and sixth form located in Hayes in the London Borough of Bromley, England.
  • C. Haskell Elementary School
    Haskell Elementary School is a public primary school located in the Granada Hills neighborhood of Los Angeles, California.
  • D. Forest Hill School
    Forest Hill School is a secondary school for boys with a co-educational sixth form located in the Sydenham area of southeast London, England.
  • E. Howe School
    Howe School is a historic former educational building in Billerica, Massachusetts, recognized for its local architectural and cultural significance.
  • 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_69d6aa5993448190a493b790b8f85010 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dfac70f481908363f9ac0b651fbe completed April 8, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96bc57a8081908abd73f4273d0666 completed April 10, 2026, 9:29 p.m.
Created at: April 8, 2026, 9:03 p.m.