Triple

T22502382
Position Surface form Disambiguated ID Type / Status
Subject Pakpak Pegagan E556306 entity
Predicate subdivisionOf P258 FINISHED
Object Pakpak 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: Pakpak language | Statement: [Pakpak Pegagan, subdivisionOf, Pakpak language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pakpak language
Context triple: [Pakpak Pegagan, subdivisionOf, Pakpak language]
  • A. Pakpak Dairi language chosen
    The Pakpak Dairi language is an Austronesian language spoken by the Pakpak (a subgroup of the Batak peoples) in northern Sumatra, Indonesia.
  • B. Embaloh language
    The Embaloh language is an Austronesian language spoken by the Embaloh people of West Kalimantan in Borneo, Indonesia.
  • C. Kalumpang language
    The Kalumpang language is an Austronesian language of Sulawesi, Indonesia, belonging to the South Sulawesi subgroup and closely associated with the Toraja linguistic area.
  • D. Napu language
    The Napu language is an Austronesian language of Central Sulawesi, Indonesia, spoken by the Napu people and classified within the Badaic subgroup.
  • E. Talaud language
    The Talaud language is an Austronesian language spoken by the indigenous population of the Talaud Islands in North Sulawesi, Indonesia.
  • 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_69e11e5445bc8190b6a9481926db3355 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15cb6b47481909855fe93e95da7e7 completed April 29, 2026, 1:19 a.m.
Created at: April 16, 2026, 8:50 p.m.