Triple

T14628349
Position Surface form Disambiguated ID Type / Status
Subject Huli people E343411 entity
Predicate language P15 FINISHED
Object Huli language E1024297 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: Huli language | Statement: [Huli people, language, Huli language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Huli language
Context triple: [Huli people, language, Huli language]
  • A. Huli language chosen
    Huli is a Papuan language spoken primarily by the Huli people of Papua New Guinea’s Southern Highlands and surrounding regions.
  • B. Kulisusu language
    The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
  • C. Buli language
    Buli is a Gur language spoken primarily in northern Ghana by the Builsa (Buli) people.
  • D. Buli language
    Buli is an Austronesian language spoken on Halmahera Island in eastern Indonesia, known for its complex verbal morphology and membership in the South Halmahera–West New Guinea subgroup.
  • E. Haliti language
    The Haliti language, also known as Paresí, is an Arawakan indigenous language spoken by the Paresí (Haliti) people of Brazil’s Mato Grosso region.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a7c8fc81909d10c1f563d7d1e7 completed April 14, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda92c25ac8190ba931c009e7ace19 completed May 8, 2026, 9:13 a.m.
Created at: April 10, 2026, 1:26 a.m.