Triple

T14870703
Position Surface form Disambiguated ID Type / Status
Subject Upper Tanana E349734 entity
Predicate hasDialect P4251 FINISHED
Object Tetlin dialect E1083832 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: Tetlin dialect | Statement: [Upper Tanana, hasDialect, Tetlin dialect]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tetlin dialect
Context triple: [Upper Tanana, hasDialect, Tetlin dialect]
  • A. Tetlin dialect chosen
    The Tetlin dialect is a regional variety of the Upper Tanana Athabaskan language traditionally spoken by the Native community in and around Tetlin, Alaska.
  • B. Oroqen dialect
    The Oroqen dialect is a regional variety of the Tungusic Evenki language spoken primarily by the Oroqen people of northeastern China.
  • C. Kainai dialect
    The Kainai dialect is a regional variety of the Blackfoot language traditionally spoken by the Kainai (Blood) people of the Blackfoot Confederacy in Alberta, Canada.
  • D. Aitutakian dialect
    The Aitutakian dialect is a variant of the Cook Islands Māori language traditionally spoken on the island of Aitutaki in the Cook Islands.
  • E. Chevak Cup’ik dialect
    The Chevak Cup’ik dialect is a Central Alaskan Yup’ik variety spoken primarily in and around the community of Chevak, distinguished by unique phonological and lexical features within the Yup’ik language continuum.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded57967748190a7c05ebb74aacb7c completed April 15, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe65129a588190bbad294b500f411f completed May 8, 2026, 10:34 p.m.
Created at: April 10, 2026, 1:55 a.m.