Triple

T22303081
Position Surface form Disambiguated ID Type / Status
Subject Sumatran languages E551304 entity
Predicate historicalWritingSystem P1558 FINISHED
Object Rencong script 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: Rencong script | Statement: [Sumatran languages, historicalWritingSystem, Rencong script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rencong script
Context triple: [Sumatran languages, historicalWritingSystem, Rencong script]
  • A. Rencong script chosen
    The Rencong script is an ancient Brahmic-derived writing system historically used in parts of Sumatra, Indonesia, particularly for Malay and related regional languages.
  • B. Rejang script
    Rejang script is an indigenous Brahmic-derived writing system used primarily for the Rejang language of southwestern Sumatra, Indonesia.
  • C. Warang Citi script
    The Warang Citi script is an alphabetic writing system created in the 20th century for the Ho language spoken by the Ho people of eastern India.
  • D. Kikakui script
    The Kikakui script is an indigenous syllabary developed in the 19th century for writing the Mende language of Sierra Leone.
  • E. Woleai script
    Woleai script is an indigenous syllabic writing system historically used by the people of Woleai Atoll in Micronesia.
  • 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1572517588190bef6f8bfb76afb19 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:41 p.m.