Triple

T7034833
Position Surface form Disambiguated ID Type / Status
Subject Johnny Chiang E163356 entity
Predicate nativeName P15 FINISHED
Object 江啟臣
江啟臣 is a Taiwanese politician who has served as a legislator and as chairman of the Kuomintang (KMT).
 E637179 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: 江啟臣 | Statement: [Johnny Chiang, nativeName, 江啟臣]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 江啟臣
Context triple: [Johnny Chiang, nativeName, 江啟臣]
  • A. 朱立倫
    朱立倫 is a Taiwanese politician who has served as New Taipei City Mayor and Chairman of the Kuomintang (KMT).
  • B. 陳士駿
    陳士駿 is a Taiwanese-American internet entrepreneur best known as a co-founder of the video-sharing platform YouTube.
  • C. Lai Ching-te
    Lai Ching-te is a Taiwanese politician and member of the Democratic Progressive Party who serves as the current president of Taiwan (Republic of China).
  • D. Chen Chien-jen
    Chen Chien-jen is a Taiwanese epidemiologist and politician who has served in top leadership roles in Taiwan’s government, including as vice president and later as premier.
  • E. Ma Ying-jeou
    Ma Ying-jeou is a Taiwanese politician and former President of the Republic of China (Taiwan) known for his leadership of the Kuomintang and efforts to improve cross-strait relations with mainland China.
  • 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: 江啟臣
Triple: [Johnny Chiang, nativeName, 江啟臣]
Generated description
江啟臣 is a Taiwanese politician who has served as a legislator and as chairman of the Kuomintang (KMT).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 江啟臣
Target entity description: 江啟臣 is a Taiwanese politician who has served as a legislator and as chairman of the Kuomintang (KMT).
  • A. 朱立倫
    朱立倫 is a Taiwanese politician who has served as New Taipei City Mayor and Chairman of the Kuomintang (KMT).
  • B. 陳士駿
    陳士駿 is a Taiwanese-American internet entrepreneur best known as a co-founder of the video-sharing platform YouTube.
  • C. Lai Ching-te
    Lai Ching-te is a Taiwanese politician and member of the Democratic Progressive Party who serves as the current president of Taiwan (Republic of China).
  • D. Chen Chien-jen
    Chen Chien-jen is a Taiwanese epidemiologist and politician who has served in top leadership roles in Taiwan’s government, including as vice president and later as premier.
  • E. Ma Ying-jeou
    Ma Ying-jeou is a Taiwanese politician and former President of the Republic of China (Taiwan) known for his leadership of the Kuomintang and efforts to improve cross-strait relations with mainland China.
  • 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_69c6885d691c81908cf7d31083113886 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e212e28c8190bf38ce9a25d2032e completed March 27, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7759c8e408190a7d457e77a44ee26 completed March 28, 2026, 6:30 a.m.
NEDg Description generation batch_69c779acac2881909917e12072f66637 completed March 28, 2026, 6:48 a.m.
NED2 Entity disambiguation (via description) batch_69c77a0390248190ba535e7d931a4682 completed March 28, 2026, 6:49 a.m.
Created at: March 27, 2026, 2:36 p.m.