Triple

T13007285
Position Surface form Disambiguated ID Type / Status
Subject Bininj E322320 entity
Predicate speaks P741 FINISHED
Object Kunwinjku E364975 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: Kunwinjku | Statement: [Bininj, speaks, Kunwinjku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kunwinjku
Context triple: [Bininj, speaks, Kunwinjku]
  • A. Kunwinjku chosen
    Kunwinjku is an Aboriginal Australian language and cultural group traditionally associated with western Arnhem Land in the Northern Territory.
  • B. Kwinana
    Kwinana is an industrial and residential suburb in the southern Perth metropolitan area of Western Australia, known for its heavy industry and coastal location.
  • C. Kuwarra
    Kuwarra is an Australian Aboriginal language variety spoken by Indigenous communities in the Western Desert region.
  • D. Kiriwina
    Kiriwina is the main and most populous island of the Trobriand Islands in Papua New Guinea, known for its distinctive Melanesian culture and traditional social systems.
  • E. Koonch
    Koonch is a town in the Indian state of Uttar Pradesh, historically notable as the site of a significant battle during the Indian Rebellion of 1857.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e9b27ec8190815c40a05b9ba7d0 completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbc5c9a88190b70bda472bf3b062 completed May 3, 2026, 4:15 a.m.
Created at: April 9, 2026, 8:48 p.m.