Triple

T15269133
Position Surface form Disambiguated ID Type / Status
Subject Yolngu Matha E364974 entity
Predicate hasPart P35 FINISHED
Object Gumatj E353986 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: Gumatj | Statement: [Yolngu Matha, hasPart, Gumatj]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gumatj
Context triple: [Yolngu Matha, hasPart, Gumatj]
  • A. Gumatj chosen
    Gumatj is a Yolngu Aboriginal Australian language spoken in northeast Arnhem Land, closely associated with the Gumatj people and their cultural and political expressions.
  • B. Mudjimba
    Mudjimba is a coastal suburb on Queensland’s Sunshine Coast in Australia, known for its beaches and relaxed seaside atmosphere.
  • C. Galmudug
    Galmudug is a federal member state in central Somalia, encompassing parts of the Galguduud and Mudug regions and functioning with its own regional government.
  • D. Goongarrie
    Goongarrie is a small rural locality in Western Australia known historically for gold mining and its proximity to the Goongarrie National Park.
  • E. Nimanburru
    Nimanburru are an Aboriginal Australian people traditionally associated with the coastal region of the Kimberley in Western Australia.
  • 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_69d85a0f08408190b3c3259ae35d79d2 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0094ca9ac8190a1f97a7b74c96cd5 completed April 15, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3aeb59c8190a39ccb4df7815ed0 completed May 9, 2026, 11:30 p.m.
Created at: April 10, 2026, 3:14 a.m.