Triple

T9044710
Position Surface form Disambiguated ID Type / Status
Subject McCune–Reischauer E216724 entity
Predicate canRomanize P23170 FINISHED
Object Hanja
Hanja are the traditional Chinese characters historically used in Korean writing, primarily for scholarly, legal, and proper-name purposes alongside the native Hangul script.
E139773 NE FINISHED

How this triple was built (5 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: Hanja | Statement: [McCune–Reischauer, canRomanize, Hanja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanja
Context triple: [McCune–Reischauer, canRomanize, Hanja]
  • A. Hanja
    Hanja is the set of traditional Chinese characters historically used to write Korean, especially for proper names, academic terms, and classical texts.
  • B. Hangul
    Hangul is the native alphabetic writing system of the Korean language, renowned for its scientific design and ease of learning.
  • C. Yi script
    Yi script is a traditional logographic and syllabic writing system used to represent the Yi languages of southwestern China.
  • D. Hangul Jamo
    Hangul Jamo is a Unicode block that encodes the individual consonant and vowel letters used to write the Korean Hangul script.
  • E. Hangul Syllables
    Hangul Syllables is the Unicode block that encodes the precomposed modern Korean syllabic characters used for writing Hangul.
  • 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: Hanja
Triple: [McCune–Reischauer, canRomanize, Hanja]
Generated description
Hanja are the traditional Chinese characters historically used in Korean writing, primarily for scholarly, legal, and proper-name purposes alongside the native Hangul script.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hanja
Target entity description: Hanja are the traditional Chinese characters historically used in Korean writing, primarily for scholarly, legal, and proper-name purposes alongside the native Hangul script.
  • A. Hanja chosen
    Hanja is the set of traditional Chinese characters historically used to write Korean, especially for proper names, academic terms, and classical texts.
  • B. Hangul
    Hangul is the native alphabetic writing system of the Korean language, renowned for its scientific design and ease of learning.
  • C. Yi script
    Yi script is a traditional logographic and syllabic writing system used to represent the Yi languages of southwestern China.
  • D. Hangul Jamo
    Hangul Jamo is a Unicode block that encodes the individual consonant and vowel letters used to write the Korean Hangul script.
  • E. Hangul Syllables
    Hangul Syllables is the Unicode block that encodes the precomposed modern Korean syllabic characters used for writing Hangul.
  • F. None of above.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: canRomanize
Context triple: [McCune–Reischauer, canRomanize, Hanja]
  • A. hasRomanizationOf
    Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
  • B. usesRomanNumerals
    Indicates that something represents numbers or sequences using the Roman numeral system rather than standard Arabic digits.
  • C. hasRomanizationStandard chosen
    Indicates that an entity’s romanized form follows a specified romanization standard or system.
  • D. hasRomanizationContrast
    Indicates that there is a meaningful difference between two or more romanized representations of the same original form.
  • E. romanizationOccurred
    Indicates that a process of converting text from one writing system into the Roman (Latin) alphabet has taken place.
  • F. None of above.

Provenance (6 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_69ca83d22d488190adbce5e020e9cd1d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6b137cec8190bd1b812c10d9542a completed April 1, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69cffdb868e48190b9d193025cb5b9a2 completed April 3, 2026, 5:49 p.m.
NEDg Description generation batch_69d000d2c5688190b014ce33c04ff875 completed April 3, 2026, 6:02 p.m.
NED2 Entity disambiguation (via description) batch_69d001a1056c819083793547dbd4b1ee completed April 3, 2026, 6:06 p.m.
PD Predicate disambiguation batch_69cc5ee566b081909e3cdaf551dbd0ec completed March 31, 2026, 11:55 p.m.
Created at: March 30, 2026, 7:09 p.m.