Triple

T4072168
Position Surface form Disambiguated ID Type / Status
Subject X̱aad Kíl E86672 entity
Predicate instanceOf P0 FINISHED
Object Haida language C15087 CONCEPT FINISHED

How this triple was built (1 step)

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.

CD Concept disambiguation gpt-5-mini-2025-08-07
Target class: Haida language
Context triple: [X̱aad Kíl, instanceOf, Haida language]
  • A. Hokan language
    Hokan language is a proposed but controversial grouping of several Native American language families and isolates of western North America, hypothesized to share a distant common ancestor.
  • B. Inuit language
    Inuit language is a group of closely related Indigenous languages spoken across the Arctic regions of Alaska, Canada, and Greenland, characterized by polysynthetic word formation and rich expression of environmental and cultural concepts.
  • C. Great Andamanese language
    The Great Andamanese language is an endangered mixed language spoken by the indigenous Great Andamanese people of the Andaman Islands, combining elements from several original Andamanese languages with influences from Hindi and other contact languages.
  • D. Numic language
    A Numic language is any member of a branch of the Uto-Aztecan language family spoken traditionally by Indigenous peoples of the Great Basin and surrounding regions of the western United States, including languages such as Northern Paiute, Shoshoni, and Comanche.
  • E. Caddoan language
    A Caddoan language is any member of a small family of Indigenous languages of the central United States, historically spoken by Caddo, Wichita, Pawnee, and related peoples, characterized by complex verb morphology and now mostly endangered or extinct.
  • F. None of above. chosen

Provenance (1 batch)

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_69aed93ebe448190a1f1686e28740ac9 completed March 9, 2026, 2:29 p.m.
Created at: March 9, 2026, 3:38 p.m.