Triple

T5846367
Position Surface form Disambiguated ID Type / Status
Subject Mandailing language E129721 entity
Predicate writingSystem P454 FINISHED
Object Batak script E123201 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: Batak script | Statement: [Mandailing language, writingSystem, Batak script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Batak script
Context triple: [Mandailing language, writingSystem, Batak script]
  • A. Batak script chosen
    Batak script is an indigenous writing system from northern Sumatra historically used to write the various Batak languages.
  • B. Tagbanwa script
    Tagbanwa script is an indigenous Brahmic-derived writing system historically used by the Tagbanwa people of Palawan in the Philippines to write their native languages.
  • C. Sundanese script
    The Sundanese script is an abugida used historically and in modern times to write the Sundanese language of West Java, Indonesia.
  • D. Lontara script
    The Lontara script is an indigenous writing system traditionally used by the Bugis and Makassarese peoples of South Sulawesi, Indonesia, to write their Austronesian languages.
  • E. Rejang script
    Rejang script is an indigenous Brahmic-derived writing system used primarily for the Rejang language of southwestern Sumatra, Indonesia.
  • 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_69c0b0fb0f68819091018926ee4c7bb8 completed March 23, 2026, 3:18 a.m.
Created at: March 22, 2026, 3:55 p.m.