Triple

T21824880
Position Surface form Disambiguated ID Type / Status
Subject Taa E538823 entity
Predicate languageFamily P1047 FINISHED
Object Tuu 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: Tuu languages | Statement: [Taa, languageFamily, Tuu languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tuu languages
Context triple: [Taa, languageFamily, Tuu languages]
  • A. Tuu languages chosen
    The Tuu languages are a small group of highly endangered click languages of southern Africa, traditionally spoken by some Khoisan hunter-gatherer communities.
  • B. Tani languages
    The Tani languages are a subgroup of the Sino-Tibetan language family spoken primarily in Arunachal Pradesh and adjoining regions of Northeast India by various indigenous communities.
  • C. Taman languages
    Taman languages are a small group of closely related Nilo-Saharan languages spoken primarily in eastern Chad and western Sudan.
  • D. Wintuan languages
    Wintuan languages are a small family of Native American languages historically spoken in northern California, often grouped within the proposed Penutian phylum.
  • E. Teke-Eboo languages
    The Teke-Eboo languages are a subgroup of Bantu languages spoken primarily by Teke-related communities in Central Africa, especially in the Republic of the Congo and surrounding regions.
  • 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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f091307d408190a92b65c3f39682a8 completed April 28, 2026, 10:51 a.m.
Created at: April 16, 2026, 6:54 p.m.