Triple

T5810503
Position Surface form Disambiguated ID Type / Status
Subject Pakpak Dairi language E128855 entity
Predicate isSpokenBySubgroupOf P17311 FINISHED
Object Batak peoples E22000 NE FINISHED

How this triple was built (3 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: Batak peoples | Statement: [Pakpak Dairi language, isSpokenBySubgroupOf, Batak peoples]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Batak peoples
Context triple: [Pakpak Dairi language, isSpokenBySubgroupOf, Batak peoples]
  • A. Batak chosen
    The Batak are a group of closely related indigenous ethnic communities from North Sumatra, Indonesia, known for their distinct languages, traditional houses, and rich cultural and ritual practices.
  • B. Nias people
    The Nias people are an indigenous ethnic group from Nias Island off the western coast of North Sumatra, Indonesia, known for their megalithic culture, distinctive wooden architecture, and traditional warrior rituals.
  • C. Talaud people
    The Talaud people are an indigenous Austronesian ethnic group inhabiting the Talaud Islands in northern Indonesia, known for their seafaring traditions and distinct language and culture.
  • D. Kerinci people
    The Kerinci people are an indigenous ethnic group from the highland Kerinci region of central Sumatra, Indonesia, known for their distinct Malayic language, terraced wet-rice agriculture, and rich oral and ritual traditions.
  • E. Mongondow people
    The Mongondow people are an indigenous ethnic group from northern Sulawesi, Indonesia, known for their distinct Austronesian language and rich local traditions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isSpokenBySubgroupOf
Context triple: [Pakpak Dairi language, isSpokenBySubgroupOf, Batak peoples]
  • A. isSpokenByMinority
    Indicates that the language or dialect is used primarily by a numerically smaller or less dominant group within a larger population.
  • B. linguisticSubgroup
    Indicates that one linguistic group forms a subordinate or specialized subset within a larger linguistic group or family.
  • C. subTribeOf
    Indicates that one tribe is a subordinate or constituent part of a larger, parent tribe.
  • D. spokenByEthnicGroup chosen
    Indicates that a particular language, dialect, or speech variety is used or spoken by a specified ethnic group.
  • E. spokenByMinorityIn
    Indicates that a language or dialect is used primarily by a minority group within a specified geographic or political region.
  • F. None of above.

Provenance (4 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_69c0084788848190bcf71f6bc5d71597 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b538cd08190a7dac378898059b9 completed March 22, 2026, 5:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a1826cc081909572d9bf99d5f670 completed March 23, 2026, 2:12 a.m.
PD Predicate disambiguation batch_69c021d5ecd081908a62dd66e26f8598 completed March 22, 2026, 5:07 p.m.
Created at: March 22, 2026, 3:52 p.m.