Triple

T6696146
Position Surface form Disambiguated ID Type / Status
Subject Wetherby School E152754 entity
Predicate hasAdmissionsPolicy P58 FINISHED
Object selective admissions LITERAL 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: selective admissions | Statement: [Wetherby School, hasAdmissionsPolicy, selective admissions]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasAdmissionsPolicy
Context triple: [Wetherby School, hasAdmissionsPolicy, selective admissions]
  • A. admissionPolicy chosen
    Indicates the rules or criteria governing whether and how entities are allowed to be admitted or granted access.
  • B. hasAdmission
    Indicates that an entity possesses or is associated with a specific admission event, record, or status (such as being admitted to a place, program, or institution).
  • C. hasSubmissionPolicy
    Indicates that an entity is associated with a specific set of rules or conditions governing how submissions to it must be made.
  • D. controlsAdmissionsFor
    Indicates that one entity has authority or responsibility over managing and deciding admissions for another entity.
  • E. hasPolicySupport
    Indicates that one entity provides endorsement, backing, or approval for a specific policy associated with another entity.
  • F. None of above.

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_69c6880687b08190805278b504d1c92c completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6b5ed99e48190970805225458ce82 completed March 27, 2026, 4:53 p.m.
PD Predicate disambiguation batch_69c6ad0e1d348190af1762ea1951038e completed March 27, 2026, 4:15 p.m.
Created at: March 27, 2026, 2:05 p.m.