Triple

T1334571
Position Surface form Disambiguated ID Type / Status
Subject Kyushu dialect E28718 entity
Predicate usesScript P1587 FINISHED
Object Katakana
Katakana is one of the two main Japanese phonetic writing systems, primarily used for foreign words, onomatopoeia, emphasis, and technical or scientific terms.
 E154499 NE FINISHED

How this triple was built (4 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: Katakana | Statement: [Kyushu dialect, usesScript, Katakana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Katakana
Context triple: [Kyushu dialect, usesScript, Katakana]
  • A. Hiragana
    Hiragana is a Japanese phonetic syllabary used primarily for native words, grammatical elements, and beginners’ reading and writing.
  • B. Kanji
    Kanji are logographic characters of Chinese origin used in the Japanese writing system alongside hiragana and katakana.
  • C. 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.
  • D. Hanja
    Hanja is the set of traditional Chinese characters historically used to write Korean, especially for proper names, academic terms, and classical texts.
  • E. Hangul Jamo Extended-A
    Hangul Jamo Extended-A is a Unicode block that contains additional archaic and extended Hangul jamo characters used for representing Old Korean and specialized orthographic forms.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Katakana
Triple: [Kyushu dialect, usesScript, Katakana]
Generated description
Katakana is one of the two main Japanese phonetic writing systems, primarily used for foreign words, onomatopoeia, emphasis, and technical or scientific terms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Katakana
Target entity description: Katakana is one of the two main Japanese phonetic writing systems, primarily used for foreign words, onomatopoeia, emphasis, and technical or scientific terms.
  • A. Hiragana
    Hiragana is a Japanese phonetic syllabary used primarily for native words, grammatical elements, and beginners’ reading and writing.
  • B. Kanji
    Kanji are logographic characters of Chinese origin used in the Japanese writing system alongside hiragana and katakana.
  • C. 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.
  • D. Hanja
    Hanja is the set of traditional Chinese characters historically used to write Korean, especially for proper names, academic terms, and classical texts.
  • E. Hangul Jamo Extended-A
    Hangul Jamo Extended-A is a Unicode block that contains additional archaic and extended Hangul jamo characters used for representing Old Korean and specialized orthographic forms.
  • F. None of above. chosen

Provenance (5 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_69a498561a508190a3e1bc137c2b866a completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c1eb119881909dd5fbf728d9e8ba completed March 1, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc62978c08190be285167cf579f9f completed March 8, 2026, 12:43 a.m.
NEDg Description generation batch_69acc8837400819084e2de10b7916a5f completed March 8, 2026, 12:53 a.m.
NED2 Entity disambiguation (via description) batch_69acc8e54728819081bdbf48df1a3fb6 completed March 8, 2026, 12:55 a.m.
Created at: March 1, 2026, 7:55 p.m.