Triple

T196617
Position Surface form Disambiguated ID Type / Status
Subject South Korea E3830 entity
Predicate hasCity P316 FINISHED
Object Ulsan
Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
 E28895 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: Ulsan | Statement: [South Korea, hasCity, Ulsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ulsan
Context triple: [South Korea, hasCity, Ulsan]
  • A. Daegu
    Daegu is a major metropolitan city in southeastern South Korea known for its textile industry, electronics manufacturing, and cultural festivals.
  • B. Busan
    Busan is South Korea’s second-largest city and a major international port known for its bustling harbor, beaches, and coastal scenery.
  • C. Daejeon
    Daejeon is a major city in central South Korea known as a hub for science, technology, and research institutions.
  • D. Incheon
    Incheon is a major port city in northwestern South Korea, known for its international airport and role as a key transportation and economic hub.
  • E. Gwangju
    Gwangju is a major metropolitan city in southwestern South Korea known for its rich cultural heritage and pivotal role in the country’s pro-democracy movement.
  • 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: Ulsan
Triple: [South Korea, hasCity, Ulsan]
Generated description
Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ulsan
Target entity description: Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
  • A. Daegu
    Daegu is a major metropolitan city in southeastern South Korea known for its textile industry, electronics manufacturing, and cultural festivals.
  • B. Busan
    Busan is South Korea’s second-largest city and a major international port known for its bustling harbor, beaches, and coastal scenery.
  • C. Daejeon
    Daejeon is a major city in central South Korea known as a hub for science, technology, and research institutions.
  • D. Incheon
    Incheon is a major port city in northwestern South Korea, known for its international airport and role as a key transportation and economic hub.
  • E. Gwangju
    Gwangju is a major metropolitan city in southwestern South Korea known for its rich cultural heritage and pivotal role in the country’s pro-democracy movement.
  • 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_69a2548debd48190ae3a06d6e65b53c6 completed Feb. 28, 2026, 2:35 a.m.
NER Named-entity recognition batch_69a2598594388190a56f36fa036eac84 completed Feb. 28, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69a35878158c81908fba5b3cb4bfd054 completed Feb. 28, 2026, 9:04 p.m.
NEDg Description generation batch_69a3598f22a08190898aec7b86cc06f4 completed Feb. 28, 2026, 9:09 p.m.
NED2 Entity disambiguation (via description) batch_69a359f3ee8c8190834a6e2dd90bc062 completed Feb. 28, 2026, 9:11 p.m.
Created at: Feb. 28, 2026, 2:41 a.m.