Triple

T23473429
Position Surface form Disambiguated ID Type / Status
Subject Kallahan languages E570189 entity
Predicate closelyRelatedTo P37 FINISHED
Object Kankanay 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: Kankanay language | Statement: [Kallahan languages, closelyRelatedTo, Kankanay language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kankanay language
Context triple: [Kallahan languages, closelyRelatedTo, Kankanay language]
  • A. Kanembu language
    The Kanembu language is a Saharan language spoken primarily in Chad by the Kanembu people, closely related to the Tebu languages and used historically in the Kanem-Bornu Empire.
  • B. Kankanaey language chosen
    The Kankanaey language is an Austronesian language spoken by the Kankanaey people of the northern Philippines, particularly in the Cordillera region of Luzon.
  • C. Kanakanavu language
    The Kanakanavu language is an endangered Austronesian language spoken by the Kanakanavu indigenous people of central-southern Taiwan.
  • D. Nankani language
    The Nankani language is a Gur language spoken primarily by the Nankani people in northern Ghana and parts of Burkina Faso.
  • E. Kandas language
    Kandas is an Oceanic language of the Western Bismarck subgroup, spoken in the Bismarck Archipelago of Papua New Guinea.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a70244208190bbd8f58ac16d4399 completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:58 p.m.