Triple

T23485409
Position Surface form Disambiguated ID Type / Status
Subject Kate Festival E570519 entity
Predicate languageUsed P238 FINISHED
Object Cham 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: Cham language | Statement: [Kate Festival, languageUsed, Cham language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cham language
Context triple: [Kate Festival, languageUsed, Cham language]
  • A. Cham language chosen
    Cham language is an Austronesian language historically spoken by the Cham people of mainland Southeast Asia, particularly in present-day Vietnam and Cambodia.
  • B. Chamba language
    The Chamba language is a Niger-Congo language spoken by the Chamba people of Nigeria and Cameroon.
  • C. Chambri language
    Chambri language is a Papuan language spoken by the Chambri (Tchambuli) people of the Sepik region in Papua New Guinea.
  • D. Tai Khamyang language
    The Tai Khamyang language is an endangered Southwestern Tai language spoken by the Khamyang ethnic community in parts of Northeast India, notable for its close relation to other Tai languages of the region and its ongoing revitalization efforts.
  • E. Rengma language
    Rengma language is a Tibeto-Burman language spoken primarily by the Rengma Naga people in the northeastern region of India.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7538a8c8190b7effcc39a3f9787 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:03 p.m.