Triple

T14372267
Position Surface form Disambiguated ID Type / Status
Subject offshore and engineering division E356384 entity
Predicate locationOfParentHeadquarters P11921 FINISHED
Object Geoje, South Korea
Geoje, South Korea is a coastal city and island known as a major hub for shipbuilding and offshore engineering industries.
E1095383 NE FINISHED

How this triple was built (5 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: Geoje, South Korea | Statement: [offshore and engineering division, locationOfParentHeadquarters, Geoje, South Korea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geoje, South Korea
Context triple: [offshore and engineering division, locationOfParentHeadquarters, Geoje, South Korea]
  • A. Bupyong, South Korea
    Bupyong, South Korea is an industrial district in Incheon known for its major automotive manufacturing facilities and dense urban development.
  • B. Osan, South Korea
    Osan is a city in Gyeonggi Province, South Korea, known for its proximity to Osan Air Base and its role as a transportation and commercial hub south of Seoul.
  • C. Jinju, South Korea
    Jinju, South Korea is a historic city in South Gyeongsang Province known for its riverside fortress, role in the Imjin War, and annual lantern festival.
  • D. Suwon, South Korea
    Suwon, South Korea is a major city just south of Seoul known for its high-tech industry and the UNESCO-listed Hwaseong Fortress.
  • E. Daegu, South Korea
    Daegu, South Korea is a major city in the southeastern part of the country known for its role as an industrial, cultural, and educational center.
  • 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: Geoje, South Korea
Triple: [offshore and engineering division, locationOfParentHeadquarters, Geoje, South Korea]
Generated description
Geoje, South Korea is a coastal city and island known as a major hub for shipbuilding and offshore engineering industries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Geoje, South Korea
Target entity description: Geoje, South Korea is a coastal city and island known as a major hub for shipbuilding and offshore engineering industries.
  • A. Bupyong, South Korea
    Bupyong, South Korea is an industrial district in Incheon known for its major automotive manufacturing facilities and dense urban development.
  • B. Osan, South Korea
    Osan is a city in Gyeonggi Province, South Korea, known for its proximity to Osan Air Base and its role as a transportation and commercial hub south of Seoul.
  • C. Jinju, South Korea
    Jinju, South Korea is a historic city in South Gyeongsang Province known for its riverside fortress, role in the Imjin War, and annual lantern festival.
  • D. Suwon, South Korea
    Suwon, South Korea is a major city just south of Seoul known for its high-tech industry and the UNESCO-listed Hwaseong Fortress.
  • E. Daegu, South Korea
    Daegu, South Korea is a major city in the southeastern part of the country known for its role as an industrial, cultural, and educational center.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locationOfParentHeadquarters
Context triple: [offshore and engineering division, locationOfParentHeadquarters, Geoje, South Korea]
  • A. hasParentCompanyHeadquarters chosen
    Indicates that a company’s parent organization has its main headquarters located at a specified place.
  • B. headquartersLocation
    Indicates the place where an organization’s main administrative center or principal office is located.
  • C. headquartersSuccessorOrganizationLocation
    Indicates that the location served as the headquarters for a successor organization that followed a previous entity.
  • D. organizationHeadquarteredInCountry
    Indicates that an organization’s main headquarters or principal place of business is located within a specified country.
  • E. headquartersLocationOfFoundedOrganization
    Indicates that a location serves as the headquarters of an organization that was founded there.
  • F. None of above.

Provenance (6 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fb2082c8190b42cc5f2bab4f574 completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c5363a081909681b54c1d8218dc completed May 8, 2026, 2:37 a.m.
NEDg Description generation batch_69fd4e795948819097c43e30902f1654 completed May 8, 2026, 2:46 a.m.
NED2 Entity disambiguation (via description) batch_69fd4f04d7ec819095b64d4811440166 completed May 8, 2026, 2:48 a.m.
PD Predicate disambiguation batch_69de2a9cb3e081909f6b33fdd939bb9e completed April 14, 2026, 11:53 a.m.
Created at: April 10, 2026, 1:15 a.m.