Triple

T8187283
Position Surface form Disambiguated ID Type / Status
Subject Imjin River E191216 entity
Predicate nearCity P350 FINISHED
Object Yeoncheon
Yeoncheon is a county in Gyeonggi Province, South Korea, known for its location near the Demilitarized Zone (DMZ) and its significant historical and military sites.
 E727747 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: Yeoncheon | Statement: [Imjin River, nearCity, Yeoncheon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yeoncheon
Context triple: [Imjin River, nearCity, Yeoncheon]
  • A. Myeongneung
    Myeongneung is one of the royal burial sites from Korea’s Joseon Dynasty, forming part of the UNESCO-listed Royal Tombs complex.
  • B. Anseongcheon
    Anseongcheon is a river in South Korea that flows through the city of Pyeongtaek in Gyeonggi Province.
  • C. Yudeungcheon
    Yudeungcheon is a river in Daejeon, South Korea, known for flowing through the city’s urban areas and serving as a local recreational and ecological space.
  • D. Hwangnyeongsan
    Hwangnyeongsan is a mountain in Busan, South Korea, known for its panoramic city views and popular hiking trails.
  • E. Hwanggujicheon
    Hwanggujicheon is a stream in Osan, South Korea, that serves as a local waterway and natural feature of the city’s landscape.
  • 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: Yeoncheon
Triple: [Imjin River, nearCity, Yeoncheon]
Generated description
Yeoncheon is a county in Gyeonggi Province, South Korea, known for its location near the Demilitarized Zone (DMZ) and its significant historical and military sites.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yeoncheon
Target entity description: Yeoncheon is a county in Gyeonggi Province, South Korea, known for its location near the Demilitarized Zone (DMZ) and its significant historical and military sites.
  • A. Myeongneung
    Myeongneung is one of the royal burial sites from Korea’s Joseon Dynasty, forming part of the UNESCO-listed Royal Tombs complex.
  • B. Anseongcheon
    Anseongcheon is a river in South Korea that flows through the city of Pyeongtaek in Gyeonggi Province.
  • C. Yudeungcheon
    Yudeungcheon is a river in Daejeon, South Korea, known for flowing through the city’s urban areas and serving as a local recreational and ecological space.
  • D. Hwangnyeongsan
    Hwangnyeongsan is a mountain in Busan, South Korea, known for its panoramic city views and popular hiking trails.
  • E. Hwanggujicheon
    Hwanggujicheon is a stream in Osan, South Korea, that serves as a local waterway and natural feature of the city’s landscape.
  • 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_69ca82c5b6948190a583c096fb0a6c71 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4d9e01208190842170abf62d9afb completed March 31, 2026, 4:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc68ea260819094ae0f87abdd8041 completed April 2, 2026, 1:29 a.m.
NEDg Description generation batch_69cdcc8439cc8190b00ce9b0781d0544 completed April 2, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69cdcdd1a0c08190aa15e665a38945e7 completed April 2, 2026, 2 a.m.
Created at: March 30, 2026, 5:41 p.m.