Triple

T18674229
Position Surface form Disambiguated ID Type / Status
Subject Tāmaki Makaurau E456557 entity
Predicate hasLandmark P105 FINISHED
Object Auckland Domain 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: Auckland Domain | Statement: [Tāmaki Makaurau, hasLandmark, Auckland Domain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Auckland Domain
Context triple: [Tāmaki Makaurau, hasLandmark, Auckland Domain]
  • A. Auckland Domain chosen
    Auckland Domain is a large historic public park in central Auckland, New Zealand, known for its expansive green spaces, sports fields, walking paths, and cultural attractions.
  • B. Whitireia New Zealand
    Whitireia New Zealand is a tertiary education institute based in Porirua, New Zealand, offering a range of vocational and academic programs.
  • C. Auckland waterfront
    The Auckland waterfront is a revitalized harborside area of Auckland, New Zealand, known for its marinas, public spaces, dining and entertainment precincts, and views over the Waitematā Harbour.
  • D. Te Kuiti Domain
    Te Kuiti Domain is a public park and sports reserve in Te Kuiti, New Zealand, used for community recreation and outdoor events.
  • E. Pukekohe
    Pukekohe is a town in the Auckland Region of New Zealand, known for its rich agricultural land and motor racing circuit.
  • 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_69d8d38f72b4819090a935175d9ca8af completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e556b41cd881908f37bf7c85e96559 completed April 19, 2026, 10:27 p.m.
Created at: April 10, 2026, 11:48 a.m.