Triple

T20016185
Position Surface form Disambiguated ID Type / Status
Subject Macro-Jê languages E494723 entity
Predicate hasSubfamily P747 FINISHED
Object Jê languages 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: Jê languages | Statement: [Macro-Jê languages, hasSubfamily, Jê languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jê languages
Context triple: [Macro-Jê languages, hasSubfamily, Jê languages]
  • A. Jê languages chosen
    The Jê languages are a branch of the Macro-Jê language family spoken by various Indigenous peoples of central and northern Brazil, known for their complex phonology and rich oral traditions.
  • B. Teda–Daza languages
    The Teda–Daza languages are a closely related pair of Saharan languages spoken primarily by the Toubou people across Chad, Niger, and Libya.
  • C. Daju languages
    The Daju languages are a small group of closely related Eastern Sudanic languages spoken primarily in parts of Sudan and Chad.
  • D. Jarrakan languages
    The Jarrakan languages are a small family of closely related Aboriginal Australian languages spoken in the eastern Kimberley region of Western Australia.
  • E. Jarawan languages
    Jarawan languages are a small group of Bantoid (often considered Bantu-related) languages spoken primarily in parts of Nigeria and Cameroon.
  • 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.