Triple

T3955289
Position Surface form Disambiguated ID Type / Status
Subject Wu dialects E84960 entity
Predicate hasSubgroup P747 FINISHED
Object Taizhou Wu
Taizhou Wu is a regional variety of the Wu group of Chinese dialects spoken primarily in and around Taizhou in Zhejiang province.
E402909 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: Taizhou Wu | Statement: [Wu dialects, hasSubgroup, Taizhou Wu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taizhou Wu
Context triple: [Wu dialects, hasSubgroup, Taizhou Wu]
  • A. Wu Qingyuan
    Wu Qingyuan, better known internationally as Go Seigen, was a Chinese-born Japanese Go master widely regarded as one of the greatest and most innovative players in the history of the game.
  • B. Ye Zhengxian
    Ye Zhengxian is known primarily as a child of the prominent Chinese military leader Ye Ting.
  • C. Zhang Wenqi
    Zhang Wenqi is a Chinese basketball player best known for having played professionally for the Shanghai Sharks in the Chinese Basketball Association.
  • D. Wu Jingyu
    Wu Jingyu is a Chinese taekwondo athlete and multiple-time Olympic gold medalist renowned as one of the sport’s most successful competitors.
  • E. Wu Yi
    Wu Yi is a Chinese politician who served as Vice Premier of the State Council and was widely known for her leadership in economic policy and public health crises such as the SARS outbreak.
  • 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: Taizhou Wu
Triple: [Wu dialects, hasSubgroup, Taizhou Wu]
Generated description
Taizhou Wu is a regional variety of the Wu group of Chinese dialects spoken primarily in and around Taizhou in Zhejiang province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taizhou Wu
Target entity description: Taizhou Wu is a regional variety of the Wu group of Chinese dialects spoken primarily in and around Taizhou in Zhejiang province.
  • A. Wu Qingyuan
    Wu Qingyuan, better known internationally as Go Seigen, was a Chinese-born Japanese Go master widely regarded as one of the greatest and most innovative players in the history of the game.
  • B. Ye Zhengxian
    Ye Zhengxian is known primarily as a child of the prominent Chinese military leader Ye Ting.
  • C. Zhang Wenqi
    Zhang Wenqi is a Chinese basketball player best known for having played professionally for the Shanghai Sharks in the Chinese Basketball Association.
  • D. Wu Jingyu
    Wu Jingyu is a Chinese taekwondo athlete and multiple-time Olympic gold medalist renowned as one of the sport’s most successful competitors.
  • E. Wu Yi
    Wu Yi is a Chinese politician who served as Vice Premier of the State Council and was widely known for her leadership in economic policy and public health crises such as the SARS outbreak.
  • 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_69aed934fbfc8190847068e4546de963 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef93d742c81908639c843193d78fd completed March 9, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533aea08c8190b83d83e3ba89848c completed March 14, 2026, 10:08 a.m.
NEDg Description generation batch_69b537f7e2e481909b7a337c130bca7a completed March 14, 2026, 10:27 a.m.
NED2 Entity disambiguation (via description) batch_69b538a7f8e4819087a74e96255e7c45 completed March 14, 2026, 10:30 a.m.
Created at: March 9, 2026, 3:30 p.m.