Triple

T16760667
Position Surface form Disambiguated ID Type / Status
Subject Red Sea Region E407333 entity
Predicate hasLanguage P15 FINISHED
Object Saho language E416298 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: Saho language | Statement: [Red Sea Region, hasLanguage, Saho language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saho language
Context triple: [Red Sea Region, hasLanguage, Saho language]
  • A. Saho language chosen
    The Saho language is an Afroasiatic Cushitic language spoken primarily by the Saho people in Eritrea and northern Ethiopia.
  • B. Sa’och language
    The Sa’och language is an endangered Austroasiatic language spoken by the Sa’och people of Cambodia and Thailand, belonging to the Pearic branch.
  • C. Shekkacho language
    The Shekkacho language is an Afroasiatic Omotic language spoken primarily by the Shekka people in the Sheka Zone of southwestern Ethiopia.
  • D. Sanglechi language
    The Sanglechi language is an Eastern Iranian language spoken by a small community in the Sanglech Valley region of Afghanistan and Tajikistan.
  • E. Sidama language
    The Sidama language is a Cushitic language spoken primarily by the Sidama people in southern Ethiopia.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abec638c81909d71ff452a4123c9 completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52d077081908080c61da67e0032 completed May 10, 2026, 3:33 p.m.
Created at: April 10, 2026, 5:21 a.m.