Triple

T23387834
Position Surface form Disambiguated ID Type / Status
Subject Chakma people E593931 entity
Predicate writingSystem P454 FINISHED
Object Chakma 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: Chakma script | Statement: [Chakma people, writingSystem, Chakma script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chakma script
Context triple: [Chakma people, writingSystem, Chakma script]
  • A. Chakma script chosen
    Chakma script is an abugida used primarily by the Chakma people of Bangladesh and India to write the Chakma language and related liturgical texts.
  • B. Meitei Mayek script
    The Meitei Mayek script is an indigenous writing system of the Meitei people of Manipur, India, historically used for their language and now revived for cultural and literary purposes.
  • C. Ahom script
    The Ahom script is an abugida historically used to write the Tai Ahom language of the Ahom people in what is now Assam, India.
  • D. Chakma language
    The Chakma language is an Indo-Aryan language spoken primarily by the Chakma people of Bangladesh and northeastern India.
  • E. Odia script
    Odia script is an abugida of the Brahmic family used primarily to write the Odia language and several other regional Indo-Aryan languages of eastern India.
  • 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_69e25d2754fc819085deea939bde60ab completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a499bad88190afca1afb2e3fddb0 completed April 29, 2026, 6:26 a.m.
Created at: April 17, 2026, 5:35 p.m.