Triple

T12420221
Position Surface form Disambiguated ID Type / Status
Subject Kŭmchŏng-gu E296748 entity
Predicate nameElement P27866 FINISHED
Object Kŭmchŏng
Kŭmchŏng is a Korean place name element that appears in geographic designations such as the district name Kŭmchŏng-gu.
E983026 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: Kŭmchŏng | Statement: [Kŭmchŏng-gu, nameElement, Kŭmchŏng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kŭmchŏng
Context triple: [Kŭmchŏng-gu, nameElement, Kŭmchŏng]
  • A. Munhwaŏ
    Munhwaŏ is the standardized form of the Korean language used in North Korea, based primarily on the Pyongyang dialect.
  • B. Koung-Khi
    Koung-Khi is an administrative department located in the West Region of Cameroon.
  • C. Nakchhong
    Nakchhong is a traditional ritual specialist and religious officiant within the Kirat Mundhum indigenous belief system.
  • D. Hungnam
    Hungnam is a port city on North Korea’s east coast that served as a major industrial center and the site of a large-scale UN evacuation during the Korean War.
  • E. Kwangde Ri
    Kwangde Ri is a prominent multi-summited mountain massif in the Khumbu region of the Nepal Himalayas, overlooking the town of Namche Bazaar.
  • 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: Kŭmchŏng
Triple: [Kŭmchŏng-gu, nameElement, Kŭmchŏng]
Generated description
Kŭmchŏng is a Korean place name element that appears in geographic designations such as the district name Kŭmchŏng-gu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kŭmchŏng
Target entity description: Kŭmchŏng is a Korean place name element that appears in geographic designations such as the district name Kŭmchŏng-gu.
  • A. Munhwaŏ
    Munhwaŏ is the standardized form of the Korean language used in North Korea, based primarily on the Pyongyang dialect.
  • B. Koung-Khi
    Koung-Khi is an administrative department located in the West Region of Cameroon.
  • C. Nakchhong
    Nakchhong is a traditional ritual specialist and religious officiant within the Kirat Mundhum indigenous belief system.
  • D. Hungnam
    Hungnam is a port city on North Korea’s east coast that served as a major industrial center and the site of a large-scale UN evacuation during the Korean War.
  • E. Kwangde Ri
    Kwangde Ri is a prominent multi-summited mountain massif in the Khumbu region of the Nepal Himalayas, overlooking the town of Namche Bazaar.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d6efd748190a5d9396a343e41e1 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f0265fc81909a6288d11b78c2f9 completed May 2, 2026, 6:14 p.m.
NEDg Description generation batch_69f6403711bc8190b214d4b06792a538 completed May 2, 2026, 6:19 p.m.
NED2 Entity disambiguation (via description) batch_69f640f543c08190b95b16a8909eebf8 completed May 2, 2026, 6:22 p.m.
Created at: April 8, 2026, 9:55 p.m.