Triple

T21286027
Position Surface form Disambiguated ID Type / Status
Subject Chang Chun-hsiung E524660 entity
Predicate givenName P17 FINISHED
Object Chun-hsiung
Chun-hsiung is the given name of Chang Chun-hsiung, a Taiwanese politician who served twice as Premier of the Republic of China (Taiwan).
E1483480 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: Chun-hsiung | Statement: [Chang Chun-hsiung, givenName, Chun-hsiung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chun-hsiung
Context triple: [Chang Chun-hsiung, givenName, Chun-hsiung]
  • A. Hsiao-chang
    Hsiao-chang is a member of the Chiang family, a prominent political dynasty in modern Chinese and Taiwanese history.
  • B. Chien Hsin
    Chien Hsin is a notable individual bearing the surname Chien, recognized for achievements that distinguish them among others with the same family name.
  • C. Chih-chung
    Chih-chung is an alternative romanization of the Chinese given name Zhizhong, used in older or non–pinyin transcription systems.
  • D. Chao Chunghsiung
    Chao Chunghsiung is an individual whose family name is Chao, likely of Chinese or Taiwanese origin.
  • E. Ke Chieh
    Ke Chieh is the Taiwanese romanization of Ke Jie, the Chinese professional Go player renowned for being one of the world's strongest and for his high-profile matches against AI programs like AlphaGo.
  • 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: Chun-hsiung
Triple: [Chang Chun-hsiung, givenName, Chun-hsiung]
Generated description
Chun-hsiung is the given name of Chang Chun-hsiung, a Taiwanese politician who served twice as Premier of the Republic of China (Taiwan).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Chun-hsiung
Target entity description: Chun-hsiung is the given name of Chang Chun-hsiung, a Taiwanese politician who served twice as Premier of the Republic of China (Taiwan).
  • A. Hsiao-chang
    Hsiao-chang is a member of the Chiang family, a prominent political dynasty in modern Chinese and Taiwanese history.
  • B. Chien Hsin
    Chien Hsin is a notable individual bearing the surname Chien, recognized for achievements that distinguish them among others with the same family name.
  • C. Chih-chung
    Chih-chung is an alternative romanization of the Chinese given name Zhizhong, used in older or non–pinyin transcription systems.
  • D. Chao Chunghsiung
    Chao Chunghsiung is an individual whose family name is Chao, likely of Chinese or Taiwanese origin.
  • E. Ke Chieh
    Ke Chieh is the Taiwanese romanization of Ke Jie, the Chinese professional Go player renowned for being one of the world's strongest and for his high-profile matches against AI programs like AlphaGo.
  • 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d658e08190ad2f267123d53ede completed April 21, 2026, 8:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09c28f9cac8190ac735c370a0493ec completed May 17, 2026, 1:28 p.m.
NEDg Description generation batch_6a09c38ffc788190b2e1922da2d0cf2d completed May 17, 2026, 1:33 p.m.
NED2 Entity disambiguation (via description) batch_6a09c41d5e448190b18f8753c05e47cf completed May 17, 2026, 1:35 p.m.
Created at: April 16, 2026, 4:03 p.m.