Triple

T4507508
Position Surface form Disambiguated ID Type / Status
Subject Dakota E101368 entity
Predicate language P15 FINISHED
Object Dakota language E100987 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: Dakota language | Statement: [Dakota, language, Dakota language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dakota language
Context triple: [Dakota, language, Dakota language]
  • A. Dakota language chosen
    The Dakota language is a Siouan language spoken by the Dakota (Eastern Sioux) people of the Northern Plains region of North America.
  • B. Lakota language
    The Lakota language is a Native American Siouan language spoken by the Lakota people, known for its rich oral tradition and ongoing revitalization efforts.
  • C. Osage language
    The Osage language is a Siouan language traditionally spoken by the Osage people of the central United States, now the focus of revitalization and preservation efforts.
  • D. Assiniboine language
    The Assiniboine language is an Indigenous Siouan language traditionally spoken by the Assiniboine people of the Northern Plains in North America.
  • E. Hidatsa language
    The Hidatsa language is a Native American language traditionally spoken by the Hidatsa people of the Northern Plains, closely related to Crow and part of the Siouan language family.
  • 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_69bd43d175248190894dc58b5b395c26 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd570e7bb8819097f7a575384a10a8 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd6fa0e3948190b7667e3db2131c1f completed March 20, 2026, 4:02 p.m.
Created at: March 20, 2026, 1:01 p.m.