Triple

T16131291
Position Surface form Disambiguated ID Type / Status
Subject Whanganui iwi E391402 entity
Predicate hasCollectiveIdentityAround P77671 FINISHED
Object Whanganui River E97293 NE FINISHED

How this triple was built (3 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: Whanganui River | Statement: [Whanganui iwi, hasCollectiveIdentityAround, Whanganui River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Whanganui River
Context triple: [Whanganui iwi, hasCollectiveIdentityAround, Whanganui River]
  • A. Whanganui River chosen
    The Whanganui River is one of New Zealand’s longest and most culturally significant rivers, renowned for its deep spiritual importance to Māori and its scenic, winding course through the central North Island.
  • B. Waitaki River
    The Waitaki River is a major river in New Zealand known for its hydroelectric power schemes, braided channels, and role as a boundary between the Canterbury and Otago regions of the South Island.
  • C. Waikato River
    The Waikato River is New Zealand’s longest river, flowing through the central North Island and playing a key role in the region’s ecology, hydroelectric power generation, and Māori cultural heritage.
  • D. Whanganui
    Whanganui is a historic riverside city on New Zealand’s North Island, known for its Māori heritage, arts scene, and location along the Whanganui River.
  • E. Rangitīkei River
    The Rangitīkei River is a major river in New Zealand renowned for its deep gorges, scenic landscapes, and popular adventure activities such as rafting and kayaking.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCollectiveIdentityAround
Context triple: [Whanganui iwi, hasCollectiveIdentityAround, Whanganui River]
  • A. hasCollectiveCharacter
    Indicates that a group or set of entities is treated as a unified whole, sharing a collective nature or identity rather than being considered solely as separate individuals.
  • B. collectivityStatus
    Indicates the state or condition of being part of a collective group versus being individual or separate.
  • C. hasCollectiveRightClaim
    Indicates that a group or collective entity asserts or holds a right or entitlement on behalf of its members.
  • D. isPartOfCommunityIdentity chosen
    Indicates that something contributes to, represents, or is recognized as a defining element of a community’s shared identity.
  • E. usedCollectiveName
    Indicates that a group of entities is referred to by a shared collective name.
  • F. None of above.

Provenance (4 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_69e2020829e88190b51ab32d22cf0259 completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00b274fa3481908b019036cd2ae627 completed May 10, 2026, 4:29 p.m.
PD Predicate disambiguation batch_69e1828518c48190a8ef3aaa46a1f639 completed April 17, 2026, 12:44 a.m.
Created at: April 10, 2026, 5:01 a.m.