Triple

T23060567
Position Surface form Disambiguated ID Type / Status
Subject Northern Formosan E574286 entity
Predicate hasMember P10 FINISHED
Object Babuza 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: Babuza language | Statement: [Northern Formosan, hasMember, Babuza language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Babuza language
Context triple: [Northern Formosan, hasMember, Babuza language]
  • A. Babuza language chosen
    The Babuza language is an endangered Austronesian language once spoken by the Babuza people in western Taiwan and classified among the Formosan languages.
  • B. Babatana language
    The Babatana language is an Oceanic language spoken by indigenous communities on Choiseul Island in the Solomon Islands.
  • C. Babanki language
    The Babanki language is a Grassfields Bantu language spoken by the Babanki people in Cameroon.
  • D. Bambassi language
    The Bambassi language is a lesser-known Afroasiatic tongue spoken by communities in western Ethiopia, classified within the North Omotic branch.
  • E. Bafut language
    The Bafut language is a Grassfields Bantu language spoken primarily by the Bafut people in the Northwest Region of Cameroon.
  • 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_69e245ba7ae48190be606dbc54120e39 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1899f359081909e89e19db3833a3d completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.