Triple

T22312594
Position Surface form Disambiguated ID Type / Status
Subject Gjerdrum E551556 entity
Predicate hasSchool P113 FINISHED
Object Ask primary 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: Ask primary school | Statement: [Gjerdrum, hasSchool, Ask primary school]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ask primary school
Context triple: [Gjerdrum, hasSchool, Ask primary school]
  • A. Primary
    Primary is a landmark 1960 American cinéma vérité documentary film that follows the 1960 Wisconsin Democratic presidential primary contest between John F. Kennedy and Hubert Humphrey.
  • B. Ask
    Ask is a small village located in the municipality of Ringerike in Buskerud county, Norway.
  • C. Ask
    Ask was a rebranded version of the Ask Jeeves web search engine, offering general internet search services.
  • D. Ask chosen
    Ask is a village in Vestland county, Norway, situated on the island of Askøy near the city of Bergen.
  • E. Young Elementary School
    Young Elementary School is a public elementary school in the Springdale Public Schools district serving early-grade students in the Springdale, Arkansas area.
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1574f97cc81909685aeef15d02af9 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:42 p.m.