Triple

T21193640
Position Surface form Disambiguated ID Type / Status
Subject Frank Hsieh E522270 entity
Predicate spouse P13 FINISHED
Object Yu Fang-chi
Yu Fang-chi is a Taiwanese public figure best known as the wife of politician and former Kaohsiung mayor Frank Hsieh.
E1477484 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: Yu Fang-chi | Statement: [Frank Hsieh, spouse, Yu Fang-chi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yu Fang-chi
Context triple: [Frank Hsieh, spouse, Yu Fang-chi]
  • A. Fan Mei-sheng
    Fan Mei-sheng is a Hong Kong actor best known for his supporting roles in classic martial arts and action films of the 1970s and 1980s.
  • B. Chien Yu-hsiu
    Chien Yu-hsiu is a Taiwanese badminton player known for competing in international men’s and mixed doubles events.
  • C. Lin Feng-jiao
    Lin Feng-jiao, better known as Joan Lin, is a retired Taiwanese actress famed for her 1970s Chinese-language film roles and as the wife of action star Jackie Chan.
  • D. Chen Ming-tong
    Chen Ming-tong is a Taiwanese politician and academic known for his role in shaping Taiwan’s cross-strait policy and serving as a key official on mainland China affairs.
  • E. Chen Wen-pei
    Chen Wen-pei is best known as the wife of Taiwanese rock musician Wu Bai.
  • 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: Yu Fang-chi
Triple: [Frank Hsieh, spouse, Yu Fang-chi]
Generated description
Yu Fang-chi is a Taiwanese public figure best known as the wife of politician and former Kaohsiung mayor Frank Hsieh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yu Fang-chi
Target entity description: Yu Fang-chi is a Taiwanese public figure best known as the wife of politician and former Kaohsiung mayor Frank Hsieh.
  • A. Fan Mei-sheng
    Fan Mei-sheng is a Hong Kong actor best known for his supporting roles in classic martial arts and action films of the 1970s and 1980s.
  • B. Chien Yu-hsiu
    Chien Yu-hsiu is a Taiwanese badminton player known for competing in international men’s and mixed doubles events.
  • C. Lin Feng-jiao
    Lin Feng-jiao, better known as Joan Lin, is a retired Taiwanese actress famed for her 1970s Chinese-language film roles and as the wife of action star Jackie Chan.
  • D. Chen Ming-tong
    Chen Ming-tong is a Taiwanese politician and academic known for his role in shaping Taiwan’s cross-strait policy and serving as a key official on mainland China affairs.
  • E. Chen Wen-pei
    Chen Wen-pei is best known as the wife of Taiwanese rock musician Wu Bai.
  • 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_69e0b51061388190aa03f19700d3ef04 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73339aaa081909d9009c58c386422 completed April 21, 2026, 8:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a099ec2ba8c81909ae6a4fcbcae00d3 completed May 17, 2026, 10:56 a.m.
NEDg Description generation batch_6a099f592488819098c54b433ce5e67e completed May 17, 2026, 10:58 a.m.
NED2 Entity disambiguation (via description) batch_6a09a033f5108190b8000934050ad55e completed May 17, 2026, 11:02 a.m.
Created at: April 16, 2026, 3:08 p.m.