Triple

T6563663
Position Surface form Disambiguated ID Type / Status
Subject 蔚山 E153846 entity
Predicate 别称 P39 FINISHED
Object 蔚山广域市 E153846 NE FINISHED

How this triple was built (3 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: 蔚山广域市 | Statement: [蔚山, 别称, 蔚山广域市]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 蔚山广域市
Context triple: [蔚山, 别称, 蔚山广域市]
  • A. 蔚山 chosen
    蔚山 is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
  • B. Gwangju, Gyeonggi
    Gwangju, Gyeonggi is a city in South Korea known for its blend of suburban residential areas, light industry, and historical sites within the Seoul Capital Area.
  • C. Paju, Gyeonggi Province
    Paju, in Gyeonggi Province, is a South Korean border city near the Demilitarized Zone known for sites like the Dorasan area and its symbolic role in inter-Korean relations.
  • D. Nam District, Busan
    Nam District, Busan is a coastal administrative district in the southern part of Busan, South Korea, known for its residential neighborhoods, universities, and seaside attractions.
  • E. Jeonju, South Korea
    Jeonju, South Korea is a historic city renowned for its well-preserved Hanok Village, traditional Korean culture, and as the birthplace of the dish bibimbap.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: 别称
Context triple: [蔚山, 别称, 蔚山广域市]
  • A. alsoKnownAs chosen
    Indicates that one entity is an alternative name, alias, or designation for another entity.
  • B. hasAffectionateNicknameFor
    Indicates that one entity uses or assigns a fond, affectionate, or endearing nickname to another entity.
  • C. isOfficialNicknameOf
    Indicates that one name is the formally recognized nickname or informal moniker used to refer to another entity.
  • D. hasNicknamedEntityType
    Indicates that an entity is associated with another entity type specifically in the role of being its nickname or informal name.
  • E. nicknamedFor
    Indicates that one entity serves as the source, inspiration, or reason for another entity’s nickname.
  • F. None of above.

Provenance (4 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6cc9c6cb0819084fec8e0beb430de completed March 27, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d55fa1bc81908f2929e835051532 completed March 27, 2026, 7:07 p.m.
PD Predicate disambiguation batch_69c6acf93cb48190b54f5dd6febd34dc completed March 27, 2026, 4:14 p.m.
Created at: March 27, 2026, 1:52 p.m.