Triple

T16128343
Position Surface form Disambiguated ID Type / Status
Subject haka E391328 entity
Predicate region P40 FINISHED
Object Aotearoa E1850 NE 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: Aotearoa | Statement: [haka, region, Aotearoa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aotearoa
Context triple: [haka, region, Aotearoa]
  • A. New Zealand chosen
    New Zealand is an island country in the southwestern Pacific Ocean known for its dramatic landscapes, indigenous Māori culture, and advanced, stable democracy.
  • B. New Zealand North Island
    New Zealand's North Island is the more populous and geothermally active of the country’s two main islands, known for its major cities, volcanic landscapes, and rich Māori cultural heritage.
  • C. NZ
    NZ is the IATA airline designator for Air New Zealand, the flag carrier airline of New Zealand.
  • D. NZ
    NZ is the vehicle registration code used for the Slovak town of Nové Zámky.
  • E. Antarctica New Zealand
    Antarctica New Zealand is the New Zealand government agency responsible for managing the country’s scientific research, environmental protection, and logistical operations in Antarctica.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e20206a6f08190aa648d2bb11e7878 completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffeef277481908ab35bbff06c827a completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 5:01 a.m.