Triple

T19989567
Position Surface form Disambiguated ID Type / Status
Subject Lower Hutt E494025 entity
Predicate hasEducationalInstitution P113 FINISHED
Object Naenae 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: Naenae College | Statement: [Lower Hutt, hasEducationalInstitution, Naenae College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Naenae College
Context triple: [Lower Hutt, hasEducationalInstitution, Naenae College]
  • A. Naenae College chosen
    Naenae College is a co-educational secondary school in Lower Hutt, New Zealand, known for serving a diverse local community.
  • B. Toroa College
    Toroa College is a residential college affiliated with the University of Otago in Dunedin, New Zealand, providing accommodation and community for its students.
  • C. Putāruru College
    Putāruru College is a secondary school located in the town of Putāruru in New Zealand.
  • D. Ōtaki College
    Ōtaki College is a secondary school located in the town of Ōtaki on New Zealand’s Kāpiti Coast.
  • E. Aorere College
    Aorere College is a co-educational secondary school located in Māngere, South Auckland, New Zealand.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65fdecf108190a5b215fd25bc4dda completed April 20, 2026, 5:18 p.m.
Created at: April 11, 2026, 3:30 p.m.