Triple

T22569706
Position Surface form Disambiguated ID Type / Status
Subject Geba script used as syllabary E558045 entity
Predicate contrastWith P278 FINISHED
Object Naxi Dongba pictographic 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: Naxi Dongba pictographic script | Statement: [Geba script used as syllabary, contrastWith, Naxi Dongba pictographic script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Naxi Dongba pictographic script
Context triple: [Geba script used as syllabary, contrastWith, Naxi Dongba pictographic script]
  • A. Dongba script chosen
    Dongba script is an ancient pictographic writing system traditionally used by Naxi priests in southwestern China for religious texts and rituals.
  • B. Tangut script
    The Tangut script is a complex, logographic writing system historically used by the Tangut people of the Western Xia dynasty in northwestern China.
  • C. Zhuang script
    The Zhuang script is a writing system used primarily to represent the Zhuang language, a major Tai language spoken in southern China.
  • D. ’Phags-pa script
    The ’Phags-pa script is a historical writing system devised in the 13th century for the Mongol Empire to serve as a unified script for multiple languages, including Mongolian and Chinese.
  • E. Tibetan script
    Tibetan script is an abugida writing system historically used for the Tibetan language and various Himalayan languages, characterized by its distinctive stacked consonants and association with Buddhist literature.
  • 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_69e11e5ae4ac8190b1f503457603d969 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15fad35448190b51a3dd639ca8568 completed April 29, 2026, 1:32 a.m.
Created at: April 16, 2026, 8:52 p.m.