Triple

T23409227
Position Surface form Disambiguated ID Type / Status
Subject Thao E560017 entity
Predicate usesScript P1587 FINISHED
Object Latin alphabet (for Thao language orthography) — NE NERFINISHED

How this triple was built (3 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: Latin alphabet (for Thao language orthography) | Statement: [Thao, usesScript, Latin alphabet (for Thao language orthography)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Latin alphabet (for Thao language orthography)
Context triple: [Thao, usesScript, Latin alphabet (for Thao language orthography)]
  • A. Latin alphabet (for Seediq language)
    The Latin alphabet for the Seediq language is an adapted Roman-based writing system used to represent the phonology and orthography of the indigenous Seediq language of Taiwan.
  • B. Latin-based Zhuang alphabet
    The Latin-based Zhuang alphabet is a modern romanized script used to write the Zhuang language spoken by the Zhuang people of southern China.
  • C. Lao script
    Lao script is an abugida writing system of the Tai-Kadai language family, primarily used to write the Lao language and closely related to the Thai script.
  • D. Vietnamese alphabet
    The Vietnamese alphabet is a modern Latin-based writing system that uses additional diacritics to represent the tones and specific sounds of the Vietnamese language.
  • E. Karelian Latin alphabet
    The Karelian Latin alphabet is the modern writing system used to represent the Karelian language with Latin-based letters.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Latin alphabet (for Thao language orthography)
Target entity description: The Latin alphabet (for Thao language orthography) is a customized Roman-based writing system adapted specifically to represent the sounds and linguistic features of the Thao language.
  • A. Latin alphabet (for Seediq language)
    The Latin alphabet for the Seediq language is an adapted Roman-based writing system used to represent the phonology and orthography of the indigenous Seediq language of Taiwan.
  • B. Latin-based Zhuang alphabet
    The Latin-based Zhuang alphabet is a modern romanized script used to write the Zhuang language spoken by the Zhuang people of southern China.
  • C. Lao script
    Lao script is an abugida writing system of the Tai-Kadai language family, primarily used to write the Lao language and closely related to the Thai script.
  • D. Vietnamese alphabet
    The Vietnamese alphabet is a modern Latin-based writing system that uses additional diacritics to represent the tones and specific sounds of the Vietnamese language.
  • E. Karelian Latin alphabet
    The Karelian Latin alphabet is the modern writing system used to represent the Karelian language with Latin-based letters.
  • F. None of above. chosen

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_69e2454b3a5881909c64773dc8a5d289 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a50fff10819094e71fb0c11b7d95 completed April 29, 2026, 6:28 a.m.
Created at: April 17, 2026, 5:38 p.m.