Triple

T19410239
Position Surface form Disambiguated ID Type / Status
Subject Kuy E485566 entity
Predicate relatedTo P37 FINISHED
Object Katu language 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: Katu language | Statement: [Kuy, relatedTo, Katu language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katu language
Context triple: [Kuy, relatedTo, Katu language]
  • A. Katu language chosen
    Katu language is an Austroasiatic language spoken by the Katu people primarily in Laos and central Vietnam.
  • B. Kato language
    Kato language is an extinct Athabaskan (Na-Dene) language once spoken by the Kato people of northern California.
  • C. Kati language
    The Kati language is a Nuristani language spoken primarily in parts of northeastern Afghanistan and adjacent regions of Pakistan.
  • D. Kiga language
    The Kiga language is a Bantu language spoken primarily by the Bakiga people of southwestern Uganda.
  • E. Kuku language
    The Kuku language is a Western Nilotic language spoken primarily by the Kuku people of South Sudan and neighboring 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62af4cc0c81909056b5e2ee574ab1 completed April 20, 2026, 1:32 p.m.
Created at: April 10, 2026, 1:37 p.m.