Triple

T3747825
Position Surface form Disambiguated ID Type / Status
Subject 대한민국 해병대 E81249 entity
Predicate garrison P75 FINISHED
Object 경기도 김포시
경기도 김포시는 인천과 서울 서북부에 인접해 한강 하구와 접한 수도권의 도시로, 군사·산업·주거 기능이 결합된 위성도시이다.
E384532 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: 경기도 김포시 | Statement: [대한민국 해병대, garrison, 경기도 김포시]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 경기도 김포시
Context triple: [대한민국 해병대, garrison, 경기도 김포시]
  • A. Gyeonggi Province
    Gyeonggi Province is a populous region in northwestern South Korea that surrounds Seoul and serves as a key political, economic, and military hub of the country.
  • B. Jincheon County
    Jincheon County is a rural administrative region in North Chungcheong Province, South Korea, known for its agricultural production and growing role as a logistics and industrial hub.
  • C. 오산시
    오산시 is a city in Gyeonggi Province, South Korea, known as a suburban industrial and residential area located south of Seoul.
  • D. Ganghwa County
    Ganghwa County is a rural island county in northwestern South Korea known for its historical sites, fortresses, and strategic location near the border with North Korea.
  • E. Jung District, Seoul
    Jung District, Seoul is a central business and administrative district of South Korea’s capital, known for its major financial institutions, government offices, and historic landmarks.
  • 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: 경기도 김포시
Triple: [대한민국 해병대, garrison, 경기도 김포시]
Generated description
경기도 김포시는 인천과 서울 서북부에 인접해 한강 하구와 접한 수도권의 도시로, 군사·산업·주거 기능이 결합된 위성도시이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 경기도 김포시
Target entity description: 경기도 김포시는 인천과 서울 서북부에 인접해 한강 하구와 접한 수도권의 도시로, 군사·산업·주거 기능이 결합된 위성도시이다.
  • A. Gyeonggi Province
    Gyeonggi Province is a populous region in northwestern South Korea that surrounds Seoul and serves as a key political, economic, and military hub of the country.
  • B. Jincheon County
    Jincheon County is a rural administrative region in North Chungcheong Province, South Korea, known for its agricultural production and growing role as a logistics and industrial hub.
  • C. 오산시
    오산시 is a city in Gyeonggi Province, South Korea, known as a suburban industrial and residential area located south of Seoul.
  • D. Ganghwa County
    Ganghwa County is a rural island county in northwestern South Korea known for its historical sites, fortresses, and strategic location near the border with North Korea.
  • E. Jung District, Seoul
    Jung District, Seoul is a central business and administrative district of South Korea’s capital, known for its major financial institutions, government offices, and historic landmarks.
  • 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_69ad8b19b7b08190a6188804e99c53e9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb6ac5ac8190934ec1a6c887a8f5 completed March 8, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4db2f5e9881908c10feafbb569f48 completed March 14, 2026, 3:51 a.m.
NEDg Description generation batch_69b4df1cfd348190831cc472de055436 completed March 14, 2026, 4:07 a.m.
NED2 Entity disambiguation (via description) batch_69b4df7b2da881908aef158d79c2834c completed March 14, 2026, 4:09 a.m.
Created at: March 8, 2026, 3:35 p.m.