Triple

T20570196
Position Surface form Disambiguated ID Type / Status
Subject Dunn School E505074 entity
Predicate name P16 FINISHED
Object Dunn School 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: Dunn School | Statement: [Dunn School, name, Dunn School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dunn School
Context triple: [Dunn School, name, Dunn School]
  • A. Dunn School chosen
    Dunn School is a private college-preparatory boarding and day school in Los Olivos, California, known for its small classes and emphasis on holistic, experiential education.
  • B. Downey School
    Downey School is a public elementary school serving young students in the town of Westwood, Massachusetts.
  • C. South School
    South School is a public elementary school serving young students in the town of Stoneham, Massachusetts.
  • D. South School
    South School is a public elementary school serving early-grade students in the New Canaan, Connecticut community.
  • E. Sheehan School
    Sheehan School is a public elementary school serving young students in the town of Westwood, Massachusetts.
  • 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_69e0b4b721588190993ac7b0a9be2736 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a5b0688190b45d0fa993c4765c completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.