Triple

T15113719
Position Surface form Disambiguated ID Type / Status
Subject Ngas E360980 entity
Predicate languageSpoken P151 FINISHED
Object Ngas language E791180 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: Ngas language | Statement: [Ngas, languageSpoken, Ngas language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ngas language
Context triple: [Ngas, languageSpoken, Ngas language]
  • A. Ngas language chosen
    The Ngas language is a West Chadic language spoken primarily in Plateau State, central Nigeria, by the Ngas (Angas) people.
  • B. Nyoongar language
    Nyoongar language is an Australian Aboriginal language traditionally spoken by the Noongar people of southwestern Western Australia.
  • C. Yinggarda language
    The Yinggarda language is an Australian Aboriginal language traditionally spoken by the Yinggarda (Yamatji) people of Western Australia’s Gascoyne region.
  • D. Waigali language
    The Waigali language is a Nuristani language spoken by the Waigal people in eastern Afghanistan.
  • E. Nitinaht language
    The Nitinaht language is a Southern Wakashan Indigenous language spoken by the Ditidaht (Nitinaht) people of Vancouver Island in British Columbia, Canada.
  • 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_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0058d786c8190937c6819255c01bd completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7eccb988190aae27dd28cf50997 completed May 9, 2026, 4:28 a.m.
Created at: April 10, 2026, 3:05 a.m.