Triple

T16941827
Position Surface form Disambiguated ID Type / Status
Subject dangwai movement E410965 entity
Predicate keyFigure P256 FINISHED
Object Yao Chia-wen
Yao Chia-wen is a prominent Taiwanese politician and democracy activist known for his leading role in the island’s opposition movement before democratization.
E1242012 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: Yao Chia-wen | Statement: [dangwai movement, keyFigure, Yao Chia-wen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yao Chia-wen
Context triple: [dangwai movement, keyFigure, Yao Chia-wen]
  • A. Hsu Huei-yu
    Hsu Huei-yu is a Taiwanese politician who has served as a leading official in cross-strait relations between Taiwan and mainland China.
  • B. Wang Yu-wen
    Wang Yu-wen is a Taiwanese actress best known for her prominent role in the acclaimed film "Eat Drink Man Woman."
  • C. Teng Yu-hsuan
    Teng Yu-hsuan is a person notable enough to be recognized as a prominent bearer of the surname Teng.
  • D. Teng Yu-wen
    Teng Yu-wen is a notable individual who bears the Chinese surname Teng.
  • E. Teng Yu-chieh
    Teng Yu-chieh is a person notable enough to be specifically distinguished as a bearer of the surname Teng.
  • 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: Yao Chia-wen
Triple: [dangwai movement, keyFigure, Yao Chia-wen]
Generated description
Yao Chia-wen is a prominent Taiwanese politician and democracy activist known for his leading role in the island’s opposition movement before democratization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yao Chia-wen
Target entity description: Yao Chia-wen is a prominent Taiwanese politician and democracy activist known for his leading role in the island’s opposition movement before democratization.
  • A. Hsu Huei-yu
    Hsu Huei-yu is a Taiwanese politician who has served as a leading official in cross-strait relations between Taiwan and mainland China.
  • B. Wang Yu-wen
    Wang Yu-wen is a Taiwanese actress best known for her prominent role in the acclaimed film "Eat Drink Man Woman."
  • C. Teng Yu-hsuan
    Teng Yu-hsuan is a person notable enough to be recognized as a prominent bearer of the surname Teng.
  • D. Teng Yu-wen
    Teng Yu-wen is a notable individual who bears the Chinese surname Teng.
  • E. Teng Yu-chieh
    Teng Yu-chieh is a person notable enough to be specifically distinguished as a bearer of the surname Teng.
  • 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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cfadec70819095ec0048ebc71016 completed April 18, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfea3bc88190acaa013169d607c5 completed May 10, 2026, 6:35 p.m.
NEDg Description generation batch_6a00d0b13f1c819091f3f8b966e36214 completed May 10, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_6a00d1ad6b7081908be76d70ad9e2075 completed May 10, 2026, 6:42 p.m.
Created at: April 10, 2026, 5:31 a.m.