Triple

T23310844
Position Surface form Disambiguated ID Type / Status
Subject Athabascan peoples E590577 entity
Predicate hasSubgroup P747 FINISHED
Object Tagish 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: Tagish | Statement: [Athabascan peoples, hasSubgroup, Tagish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tagish
Context triple: [Athabascan peoples, hasSubgroup, Tagish]
  • A. Tagish chosen
    Tagish is an endangered Athabaskan Indigenous language traditionally spoken by the Tagish people of southern Yukon in northwestern Canada.
  • B. Nechako Lakes
    Nechako Lakes is a lake-dotted region in north-central British Columbia, Canada, known for its extensive freshwater systems, forests, and outdoor recreation opportunities.
  • C. Langara
    Langara is a town located in the Indonesian province of Southeast Sulawesi.
  • D. Powell River
    Powell River is a small coastal city in southwestern British Columbia, Canada, known for its scenic waterfront, outdoor recreation, and historic townsite.
  • E. Powell River
    Powell River is a tributary waterway in the southeastern United States that flows through parts of Virginia and Tennessee before joining the Clinch River.
  • 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_69e25d1d32188190948eb76909d1dcc3 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1972acad08190bb56541b822555cd completed April 29, 2026, 5:29 a.m.
Created at: April 17, 2026, 5:06 p.m.