Triple

T15571521
Position Surface form Disambiguated ID Type / Status
Subject Towa E374252 entity
Predicate hasAlternativeName P39 FINISHED
Object Towa language E486074 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: Towa language | Statement: [Towa, hasAlternativeName, Towa language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Towa language
Context triple: [Towa, hasAlternativeName, Towa language]
  • A. Towa language chosen
    Towa is a Native American language spoken by the Towa (Jemez) people of New Mexico and is part of the Puebloan language family.
  • B. Keiga language
    The Keiga language is a Kadu (Kadugli) language spoken by the Keiga people in the Nuba Mountains region of Sudan.
  • C. Chimariko language
    The Chimariko language is an extinct Native American language once spoken in northwestern California, often classified within the proposed Hokan language family.
  • D. Sayawa language
    The Sayawa language is a Chadic language spoken primarily by the Sayawa people in Bauchi State, northeastern Nigeria.
  • E. Tai Yo language
    The Tai Yo language is a Southwestern Tai language spoken by the Tai Yo ethnic group in parts of Vietnam, Laos, and Thailand.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e2025888190a2b6240296bba13e completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4767e48190a180062688cdc245 completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:10 a.m.