Triple

T21365654
Position Surface form Disambiguated ID Type / Status
Subject Molly Craig E526903 entity
Predicate language P15 FINISHED
Object Martu Wangka 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: Martu Wangka | Statement: [Molly Craig, language, Martu Wangka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martu Wangka
Context triple: [Molly Craig, language, Martu Wangka]
  • A. Martu Wangka chosen
    Martu Wangka is an Australian Aboriginal language traditionally spoken by the Martu people of the Western Desert region of Western Australia.
  • B. Mungaoli
    Mungaoli is a town and legislative assembly constituency in the Ashoknagar district of Madhya Pradesh, India.
  • C. Illawong
    Illawong is a suburban residential area in southern Sydney, New South Wales, known for its bushland setting between the Georges and Woronora Rivers.
  • D. Rirratjingu
    Rirratjingu is an Aboriginal Australian Yolŋu clan and language group from northeast Arnhem Land in the Northern Territory.
  • E. Mungindi
    Mungindi is a remote Australian town uniquely situated on both sides of the New South Wales–Queensland border, serving as a rural service centre for the surrounding agricultural region.
  • 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_69e0b51d8a308190b09113b3b3f9bc15 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b06ec4208190b9ed3484afd85852 completed April 22, 2026, 11:26 a.m.
Created at: April 16, 2026, 5:09 p.m.