Triple

T17811923
Position Surface form Disambiguated ID Type / Status
Subject Cheongju E444728 entity
Predicate hasDistrict P459 FINISHED
Object Cheongwon-gu
Cheongwon-gu is an administrative district of the city of Cheongju in North Chungcheong Province, South Korea.
E1330839 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: Cheongwon-gu | Statement: [Cheongju, hasDistrict, Cheongwon-gu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cheongwon-gu
Context triple: [Cheongju, hasDistrict, Cheongwon-gu]
  • A. Jungwon-gu
    Jungwon-gu is an administrative district (gu) of the city of Seongnam in Gyeonggi Province, South Korea, comprising residential, commercial, and cultural areas.
  • B. Sangnok-gu
    Sangnok-gu is a district of the city of Ansan in Gyeonggi Province, South Korea, known as one of its main urban and residential areas.
  • C. Kangseo-gu
    Kangseo-gu is the romanized name of Gangseo District, an administrative district of Seoul, South Korea.
  • D. Gwangjin-gu
    Gwangjin-gu is a district in eastern Seoul, South Korea, known for its universities, shopping areas, and the Konkuk University and Gangbyeon neighborhoods along the Han River.
  • E. Geumjeong-gu
    Geumjeong-gu is a district in Busan, South Korea, known for its residential areas, transportation hubs, and proximity to Geumjeongsan Mountain.
  • 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: Cheongwon-gu
Triple: [Cheongju, hasDistrict, Cheongwon-gu]
Generated description
Cheongwon-gu is an administrative district of the city of Cheongju in North Chungcheong Province, South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cheongwon-gu
Target entity description: Cheongwon-gu is an administrative district of the city of Cheongju in North Chungcheong Province, South Korea.
  • A. Jungwon-gu
    Jungwon-gu is an administrative district (gu) of the city of Seongnam in Gyeonggi Province, South Korea, comprising residential, commercial, and cultural areas.
  • B. Sangnok-gu
    Sangnok-gu is a district of the city of Ansan in Gyeonggi Province, South Korea, known as one of its main urban and residential areas.
  • C. Kangseo-gu
    Kangseo-gu is the romanized name of Gangseo District, an administrative district of Seoul, South Korea.
  • D. Gwangjin-gu
    Gwangjin-gu is a district in eastern Seoul, South Korea, known for its universities, shopping areas, and the Konkuk University and Gangbyeon neighborhoods along the Han River.
  • E. Geumjeong-gu
    Geumjeong-gu is a district in Busan, South Korea, known for its residential areas, transportation hubs, and proximity to Geumjeongsan Mountain.
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4887b5e50819098506f0b92d709b5 completed April 19, 2026, 7:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a049abe0f5c81909bee53d18f186e0c completed May 13, 2026, 3:37 p.m.
NEDg Description generation batch_6a049c461c288190955ac8cdaefc055d completed May 13, 2026, 3:44 p.m.
NED2 Entity disambiguation (via description) batch_6a049cbbc0288190be82f11e660b7dff completed May 13, 2026, 3:46 p.m.
Created at: April 10, 2026, 10:14 a.m.