Triple

T16638238
Position Surface form Disambiguated ID Type / Status
Subject North Pyongan Province E404263 entity
Predicate hasMajorCity P316 FINISHED
Object Pakchon
Pakchon is a city in North Pyongan Province, North Korea, known as a regional center for agriculture and light industry.
E1224515 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: Pakchon | Statement: [North Pyongan Province, hasMajorCity, Pakchon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pakchon
Context triple: [North Pyongan Province, hasMajorCity, Pakchon]
  • A. Seogwipo
    Seogwipo is a coastal city on South Korea’s Jeju Island known for its waterfalls, volcanic landscapes, and popular tourist attractions.
  • B. Taejongdae
    Taejongdae is a famous coastal park in Busan, South Korea, known for its dramatic seaside cliffs, dense pine forests, and panoramic ocean views.
  • C. Wanggeom-seong
    Wanggeom-seong was the principal royal city and political center of the ancient Korean kingdom of Gojoseon, traditionally regarded as Korea’s first capital.
  • D. Dangun
    Dangun is the legendary progenitor of the Korean nation, traditionally revered as the mythical king who established Korea’s first kingdom in ancient times.
  • E. Hwaseong
    Hwaseong is a city in Gyeonggi Province, South Korea, known for its rapid industrial growth and proximity to major urban centers like Suwon and Seoul.
  • 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: Pakchon
Triple: [North Pyongan Province, hasMajorCity, Pakchon]
Generated description
Pakchon is a city in North Pyongan Province, North Korea, known as a regional center for agriculture and light industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pakchon
Target entity description: Pakchon is a city in North Pyongan Province, North Korea, known as a regional center for agriculture and light industry.
  • A. Seogwipo
    Seogwipo is a coastal city on South Korea’s Jeju Island known for its waterfalls, volcanic landscapes, and popular tourist attractions.
  • B. Taejongdae
    Taejongdae is a famous coastal park in Busan, South Korea, known for its dramatic seaside cliffs, dense pine forests, and panoramic ocean views.
  • C. Wanggeom-seong
    Wanggeom-seong was the principal royal city and political center of the ancient Korean kingdom of Gojoseon, traditionally regarded as Korea’s first capital.
  • D. Dangun
    Dangun is the legendary progenitor of the Korean nation, traditionally revered as the mythical king who established Korea’s first kingdom in ancient times.
  • E. Hwaseong
    Hwaseong is a city in Gyeonggi Province, South Korea, known for its rapid industrial growth and proximity to major urban centers like Suwon and Seoul.
  • 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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378eb07388190a10e896bae7f098e completed April 18, 2026, 12:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a007dc28df48190b01c1328df24df60 completed May 10, 2026, 12:44 p.m.
NEDg Description generation batch_6a007e8cff9881908c6b86da38fc2f08 completed May 10, 2026, 12:48 p.m.
NED2 Entity disambiguation (via description) batch_6a007f53918481908d84ecf50a562266 completed May 10, 2026, 12:51 p.m.
Created at: April 10, 2026, 5:18 a.m.