Triple

T5846374
Position Surface form Disambiguated ID Type / Status
Subject Mandailing language E129721 entity
Predicate closelyRelatedTo P37 FINISHED
Object Angkola language E119354 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: Angkola language | Statement: [Mandailing language, closelyRelatedTo, Angkola language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angkola language
Context triple: [Mandailing language, closelyRelatedTo, Angkola language]
  • A. Angkola language chosen
    Angkola language is an Austronesian language of the Batak group spoken primarily by the Angkola people in North Sumatra, Indonesia.
  • B. Anuak language
    The Anuak language is a Nilotic language spoken primarily by the Anuak people of western Ethiopia and eastern South Sudan.
  • C. Anakalangu language
    The Anakalangu language is an Austronesian language spoken by communities on the island of Sumba in eastern Indonesia.
  • D. Lamaholot language
    The Lamaholot language is an Austronesian language spoken primarily in eastern Flores and nearby islands in Indonesia, known for its numerous dialects and complex verbal morphology.
  • E. Ngaju language
    The Ngaju language is an Austronesian language spoken primarily by the Ngaju Dayak people of central Kalimantan in Indonesian Borneo.
  • 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_69c0084bd31c8190a796bb6284845e83 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0351157508190a78d2a7141e0cee8 completed March 22, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a1a9ffa881908b38eeddb411c4ab completed March 23, 2026, 2:12 a.m.
Created at: March 22, 2026, 3:55 p.m.