Triple

T20016197
Position Surface form Disambiguated ID Type / Status
Subject Macro-Jê languages E494723 entity
Predicate includesLanguage P2177 FINISHED
Object Xavante language 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: Xavante language | Statement: [Macro-Jê languages, includesLanguage, Xavante language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xavante language
Context triple: [Macro-Jê languages, includesLanguage, Xavante language]
  • A. Warao language
    The Warao language is an indigenous language isolate spoken by the Warao people of northeastern Venezuela and nearby regions, particularly in the Orinoco Delta.
  • B. Juruna language
    The Juruna language is an indigenous Tupian language spoken by the Juruna (Yudjá) people of the Xingu region in Brazil.
  • C. Bororo language chosen
    The Bororo language is an indigenous Macro-Jê language of central Brazil, traditionally spoken by the Bororo people and known for its complex phonology and rich oral tradition.
  • D. Terena language
    The Terena language is an Arawakan indigenous language spoken primarily by the Terena people of Brazil’s Mato Grosso do Sul region.
  • E. Jarawa language
    The Jarawa language is an endangered Ongan language spoken by the indigenous Jarawa people of the Andaman Islands in India.
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623cb8188190b95913ffed895930 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:34 p.m.