Triple

T33384218
Position Surface form Disambiguated ID Type / Status
Subject Ngāti Kurī E854867 entity
Predicate receivedFinancialRedress P93714 FINISHED
Object approximately NZD 21 million LITERAL 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: approximately NZD 21 million | Statement: [Ngāti Kurī, receivedFinancialRedress, approximately NZD 21 million]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: receivedFinancialRedress
Context triple: [Ngāti Kurī, receivedFinancialRedress, approximately NZD 21 million]
  • A. receivedRedress
    Indicates that an entity has been given compensation, remedy, or corrective action in response to a prior harm, grievance, or injustice.
  • B. receivedSettlementAmount chosen
    Indicates that an entity has obtained a specified amount of money or value as part of a settlement.
  • C. receivedSettlementFrom
    Indicates that one party obtained a settlement payment or compensation from another party, typically as the result of a dispute, claim, or legal action.
  • D. refundForm
    Indicates that an entity is a form or process used to request or process a refund for another entity.
  • E. redemptionOutcome
    Indicates the result or consequence of a redemption process, specifying what happens or is obtained when something is redeemed.
  • F. None of above.

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_69f3496d54048190a1cb91fdd7caa6ea completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f7805ce6208190ac6dbd9c97989978 completed May 3, 2026, 5:05 p.m.
PD Predicate disambiguation batch_69f77956ec648190ba4fb7e9d83fd107 completed May 3, 2026, 4:35 p.m.
Created at: May 1, 2026, 1:35 a.m.