Triple

T21584638
Position Surface form Disambiguated ID Type / Status
Subject Mapo District E532616 entity
Predicate KoreanName P17869 FINISHED
Object 마포구
마포구는 서울특별시 서북부에 위치한 행정구로, 홍대·상암DMC 등 젊은 문화와 미디어·IT 산업이 발달한 지역이다.
 E1491925 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: 마포구 | Statement: [Mapo District, KoreanName, 마포구]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 마포구
Context triple: [Mapo District, KoreanName, 마포구]
  • A. 종로구
    종로구 is a central district in Seoul, South Korea, known as the historic and political heart of the city, home to major palaces, government institutions, and cultural landmarks.
  • B. Dongdaemun-gu
    Dongdaemun-gu is a central district in Seoul, South Korea, known for its major commercial areas, historic sites, and the iconic Dongdaemun Design Plaza.
  • C. Seodaemun-gu
    Seodaemun-gu is a central district in Seoul, South Korea, known for its major universities, historical sites, and vibrant urban neighborhoods.
  • D. Seocho District
    Seocho District is a major affluent ward in southern Seoul, South Korea, known for its legal institutions, upscale residential areas, and proximity to the Gangnam business district.
  • E. 금정구
    금정구는 부산광역시 북동부에 위치한 행정구로, 금정산과 범어사 등 자연·문화 유산이 풍부한 주거·교육 중심 지역이다.
  • 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: 마포구
Triple: [Mapo District, KoreanName, 마포구]
Generated description
마포구는 서울특별시 서북부에 위치한 행정구로, 홍대·상암DMC 등 젊은 문화와 미디어·IT 산업이 발달한 지역이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 마포구
Target entity description: 마포구는 서울특별시 서북부에 위치한 행정구로, 홍대·상암DMC 등 젊은 문화와 미디어·IT 산업이 발달한 지역이다.
  • A. 종로구
    종로구 is a central district in Seoul, South Korea, known as the historic and political heart of the city, home to major palaces, government institutions, and cultural landmarks.
  • B. Dongdaemun-gu
    Dongdaemun-gu is a central district in Seoul, South Korea, known for its major commercial areas, historic sites, and the iconic Dongdaemun Design Plaza.
  • C. Seodaemun-gu
    Seodaemun-gu is a central district in Seoul, South Korea, known for its major universities, historical sites, and vibrant urban neighborhoods.
  • D. Seocho District
    Seocho District is a major affluent ward in southern Seoul, South Korea, known for its legal institutions, upscale residential areas, and proximity to the Gangnam business district.
  • E. 금정구
    금정구는 부산광역시 북동부에 위치한 행정구로, 금정산과 범어사 등 자연·문화 유산이 풍부한 주거·교육 중심 지역이다.
  • 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_69e0c4618bec8190bcb0feb74568cbb1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb5f2cc0819095552de70eb2ad8d completed April 27, 2026, 4:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09f67cc2288190886c4124c97edb67 completed May 17, 2026, 5:10 p.m.
NEDg Description generation batch_6a09f9614ab88190806a3ed38b7ba537 completed May 17, 2026, 5:22 p.m.
NED2 Entity disambiguation (via description) batch_6a09fa3c92a8819082e454d907971b21 completed May 17, 2026, 5:26 p.m.
Created at: April 16, 2026, 6:31 p.m.