Triple

T14305538
Position Surface form Disambiguated ID Type / Status
Subject Jinhua E354684 entity
Predicate hasSubdivision P747 FINISHED
Object Yongkang
Yongkang is a county-level city in Zhejiang Province, China, known as a major manufacturing hub, especially for hardware and metal products.
E1098573 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: Yongkang | Statement: [Jinhua, hasSubdivision, Yongkang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yongkang
Context triple: [Jinhua, hasSubdivision, Yongkang]
  • A. Yongkang District
    Yongkang District is a major suburban and industrial district of Tainan City in southern Taiwan, known for its manufacturing base and growing residential communities.
  • B. Yueqing
    Yueqing is a county-level coastal city administered by Wenzhou in Zhejiang Province, China, known for its manufacturing industry and economic vitality.
  • C. Jinhua
    Jinhua is a prefecture-level city in eastern China known for its historical sites, transportation hub role, and famous local ham products.
  • D. Jiande
    Jiande was an era name used during the Northern Qi dynasty in imperial China to designate a specific reign period.
  • E. Jiande
    Jiande is a county-level city in Zhejiang Province, China, known for its scenic landscapes along the Fuchun River and its mix of historical and modern urban development.
  • 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: Yongkang
Triple: [Jinhua, hasSubdivision, Yongkang]
Generated description
Yongkang is a county-level city in Zhejiang Province, China, known as a major manufacturing hub, especially for hardware and metal products.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yongkang
Target entity description: Yongkang is a county-level city in Zhejiang Province, China, known as a major manufacturing hub, especially for hardware and metal products.
  • A. Yongkang District
    Yongkang District is a major suburban and industrial district of Tainan City in southern Taiwan, known for its manufacturing base and growing residential communities.
  • B. Yueqing
    Yueqing is a county-level coastal city administered by Wenzhou in Zhejiang Province, China, known for its manufacturing industry and economic vitality.
  • C. Jinhua
    Jinhua is a prefecture-level city in eastern China known for its historical sites, transportation hub role, and famous local ham products.
  • D. Jiande
    Jiande is a county-level city in Zhejiang Province, China, known for its scenic landscapes along the Fuchun River and its mix of historical and modern urban development.
  • E. Jiande
    Jiande was an era name used during the Northern Qi dynasty in imperial China to designate a specific reign period.
  • 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_69d8278ed42c8190b9f882dcce611347 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de85afabe48190926d6098047f4bcf completed April 14, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bb9947481909cd16aa1d719fbe5 completed May 8, 2026, 3:42 a.m.
NEDg Description generation batch_69fd5d16cd708190b57e47deb9b98aae completed May 8, 2026, 3:48 a.m.
NED2 Entity disambiguation (via description) batch_69fd5d8f337881908b245e63b60db249 completed May 8, 2026, 3:50 a.m.
Created at: April 10, 2026, 1:12 a.m.