Triple

T22050271
Position Surface form Disambiguated ID Type / Status
Subject Nüshu E544863 entity
Predicate UnicodeBlock P1445 FINISHED
Object Nushu 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: Nushu | Statement: [Nüshu, UnicodeBlock, Nushu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nushu
Context triple: [Nüshu, UnicodeBlock, Nushu]
  • A. Nushu chosen
    Nushu is a rare, syllabic script historically used exclusively by women in parts of Hunan, China, to write a unique form of Chinese.
  • B. Tai Nüa script
    The Tai Nüa script is an abugida used primarily by the Tai Nüa (Dai) people of China and Southeast Asia to write the Tai Nüa language.
  • C. Sorabe script
    The Sorabe script is an Arabic-derived writing system historically used by Malagasy speakers, particularly in southern Madagascar, for religious, literary, and administrative texts.
  • D. Grammata Serica
    Grammata Serica is a seminal scholarly work that systematically reconstructs and analyzes the phonology and characters of ancient Chinese, laying the foundation for modern historical Chinese linguistics.
  • E. Kawi script
    Kawi script is an ancient Brahmic-derived writing system historically used across Java and other parts of Southeast Asia to write Old Javanese and related languages.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128323fb08190b9592fd08a96cba0 completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:26 p.m.