Triple

T13713765
Position Surface form Disambiguated ID Type / Status
Subject Kbandu drum E328839 entity
Predicate usedIn P98 FINISHED
Object Kumina E65505 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: Kumina | Statement: [Kbandu drum, usedIn, Kumina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kumina
Context triple: [Kbandu drum, usedIn, Kumina]
  • A. Kumina chosen
    Kumina is a Jamaican Afro-Caribbean spiritual tradition and performance practice rooted in Central African (Kongo) heritage, known for its drumming, dancing, and ancestral spirit possession rituals.
  • B. Kumily
    Kumily is a town in the Idukki district of Kerala, India, known as a major gateway to the Periyar wildlife and spice plantation tourism region.
  • C. Caibiran
    Caibiran is a coastal municipality on Biliran Island in the Eastern Visayas region of the Philippines, known for its natural springs and rural landscape.
  • D. Kamayo
    Kamayo is an Austronesian language spoken primarily in parts of Mindanao in the Philippines, particularly in the Caraga region.
  • E. Kokama
    Kokama are an Indigenous people of the western Amazon, primarily inhabiting regions of Peru, Brazil, and Colombia, known for their distinct Kokama language and riverine culture.
  • 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd43973cf08190a417d0cca9dd314a completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d56a90081908158dcf4ee061fb6 completed May 3, 2026, 7:09 p.m.
Created at: April 9, 2026, 9:54 p.m.