Triple

T9087714
Position Surface form Disambiguated ID Type / Status
Subject Seo District, Busan E217800 entity
Predicate shortName P43 FINISHED
Object Seo-gu
Seo-gu is a coastal district in the southwestern part of Busan, South Korea, known for its port facilities, historic sites, and urban residential areas.
E823067 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: Seo-gu | Statement: [Seo District, Busan, shortName, Seo-gu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seo-gu
Context triple: [Seo District, Busan, shortName, Seo-gu]
  • A. Seo-gu
    Seo-gu is a district of the metropolitan city of Daejeon in South Korea, known for its residential areas, commercial centers, and educational institutions.
  • B. Seo-gu
    Seo-gu is an administrative district in the city of Daegu, South Korea, known primarily as a residential and commercial urban area.
  • C. Sasang-gu
    Sasang-gu is an administrative district in Busan, South Korea, known for its transportation hubs, industrial areas, and mixed residential-commercial neighborhoods.
  • D. Kangseo-gu
    Kangseo-gu is the romanized name of Gangseo District, an administrative district of Seoul, South Korea.
  • E. Sŏch'o-gu
    Sŏch'o-gu is the McCune–Reischauer romanization of Seocho District, a major administrative and residential area in southern Seoul, South Korea.
  • 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: Seo-gu
Triple: [Seo District, Busan, shortName, Seo-gu]
Generated description
Seo-gu is a coastal district in the southwestern part of Busan, South Korea, known for its port facilities, historic sites, and urban residential areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Seo-gu
Target entity description: Seo-gu is a coastal district in the southwestern part of Busan, South Korea, known for its port facilities, historic sites, and urban residential areas.
  • A. Seo-gu
    Seo-gu is a district of the metropolitan city of Daejeon in South Korea, known for its residential areas, commercial centers, and educational institutions.
  • B. Seo-gu
    Seo-gu is an administrative district in the city of Daegu, South Korea, known primarily as a residential and commercial urban area.
  • C. Sasang-gu
    Sasang-gu is an administrative district in Busan, South Korea, known for its transportation hubs, industrial areas, and mixed residential-commercial neighborhoods.
  • D. Kangseo-gu
    Kangseo-gu is the romanized name of Gangseo District, an administrative district of Seoul, South Korea.
  • E. Sŏch'o-gu
    Sŏch'o-gu is the McCune–Reischauer romanization of Seocho District, a major administrative and residential area in southern Seoul, South Korea.
  • 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_69ca83d8ab5881909d8fddae363b32b1 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc965646408190b041ab0e2d5dbc94 completed April 1, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc2ca7a081908f597e9a58920d6e completed April 5, 2026, 2:42 a.m.
NEDg Description generation batch_69d1ccb043008190a3af47b234520891 completed April 5, 2026, 2:45 a.m.
NED2 Entity disambiguation (via description) batch_69d1cd04694881909ab19cb4c11fbd20 completed April 5, 2026, 2:46 a.m.
Created at: March 30, 2026, 7:13 p.m.