Triple

T14703563
Position Surface form Disambiguated ID Type / Status
Subject Te Kā E345366 entity
Predicate weakness P7340 FINISHED
Object heart of Te Fiti E1115783 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: heart of Te Fiti | Statement: [Te Kā, weakness, heart of Te Fiti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: heart of Te Fiti
Context triple: [Te Kā, weakness, heart of Te Fiti]
  • A. heart of Te Fiti chosen
    The heart of Te Fiti is a powerful, life-giving green stone in Disney's "Moana" whose theft triggers environmental devastation and whose restoration heals the world.
  • B. Te Fiti
    Te Fiti is the powerful island goddess of creation and life in Disney's animated film "Moana."
  • C. Teiwa
    Teiwa is a Papuan language spoken on Pantar Island in eastern Indonesia, known for its complex verb morphology and membership in the Alor–Pantar language family.
  • D. Piopiotahi
    Piopiotahi is the Māori name for Milford Sound, a dramatic fiord in Fiordland National Park on New Zealand’s South Island renowned for its towering cliffs, waterfalls, and wildlife.
  • E. Koru
    Koru is a small town in western Kenya known historically for its agricultural activities and as the childhood home of former UN Secretary-General Kofi Annan.
  • 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_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb6071e5c8190bb5509c859135c2d completed April 14, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb8221a4819098937018f24a0b44 completed May 8, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:28 a.m.