Triple

T1978771
Position Surface form Disambiguated ID Type / Status
Subject United States Forces Korea E42975 entity
Predicate previousHeadquarters P12035 FINISHED
Object Yongsan Garrison
Yongsan Garrison is a former major U.S. military base in central Seoul, South Korea, that long served as the primary hub for American forces on the Korean Peninsula.
E223596 NE FINISHED

How this triple was built (5 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: Yongsan Garrison | Statement: [United States Forces Korea, previousHeadquarters, Yongsan Garrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yongsan Garrison
Context triple: [United States Forces Korea, previousHeadquarters, Yongsan Garrison]
  • A. Mangyongdae
    Mangyongdae is a historic district in Pyongyang, North Korea, known as the birthplace and commemorative site of the country's founding leader, Kim Il Sung.
  • B. Daedeok-gu
    Daedeok-gu is a district in the city of Daejeon, South Korea, known for encompassing parts of the country’s major research and science complex.
  • C. Incheon Gwangyeoksi
    Incheon Gwangyeoksi is a major metropolitan city in northwestern South Korea, known for its international airport, large seaport, and role as a key gateway to Seoul and the wider region.
  • D. Dong-gu
    Dong-gu is an administrative district of the metropolitan city of Ulsan in South Korea, known for its coastal location and industrial facilities.
  • E. Dong-gu
    Dong-gu is a district-level administrative area within the metropolitan city of Daejeon in South Korea.
  • 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: Yongsan Garrison
Triple: [United States Forces Korea, previousHeadquarters, Yongsan Garrison]
Generated description
Yongsan Garrison is a former major U.S. military base in central Seoul, South Korea, that long served as the primary hub for American forces on the Korean Peninsula.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yongsan Garrison
Target entity description: Yongsan Garrison is a former major U.S. military base in central Seoul, South Korea, that long served as the primary hub for American forces on the Korean Peninsula.
  • A. Mangyongdae
    Mangyongdae is a historic district in Pyongyang, North Korea, known as the birthplace and commemorative site of the country's founding leader, Kim Il Sung.
  • B. Daedeok-gu
    Daedeok-gu is a district in the city of Daejeon, South Korea, known for encompassing parts of the country’s major research and science complex.
  • C. Incheon Gwangyeoksi
    Incheon Gwangyeoksi is a major metropolitan city in northwestern South Korea, known for its international airport, large seaport, and role as a key gateway to Seoul and the wider region.
  • D. Dong-gu
    Dong-gu is a district-level administrative area within the metropolitan city of Daejeon in South Korea.
  • E. Dong-gu
    Dong-gu is an administrative district of the metropolitan city of Ulsan in South Korea, known for its coastal location and industrial facilities.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousHeadquarters
Context triple: [United States Forces Korea, previousHeadquarters, Yongsan Garrison]
  • A. issuerFormerHeadquartersCity
    Indicates the city where the issuer’s former headquarters were located before moving or changing.
  • B. temporaryHeadquartersLocation
    Indicates the location where an entity is serving as a temporary headquarters for an organization or operation.
  • C. headquartersLocation
    Indicates the place where an organization’s main administrative center or principal office is located.
  • D. movedHeadquartersFrom chosen
    Indicates that an entity relocated its main headquarters from one specified place to another.
  • E. headquartersFoundedAt
    Indicates that an organization's headquarters was originally established at a specific location.
  • F. None of above.

Provenance (6 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_69a8871289048190b00b0d7744b7b2b1 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb43011188190b6a41c004e9e4802 completed March 7, 2026, 5:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae032988ec8190b9012cbb77e7efa4 completed March 8, 2026, 11:15 p.m.
NEDg Description generation batch_69ae03c4faac8190a13aa0882eda3629 completed March 8, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69ae0445a9608190918a7bd45b9bf999 completed March 8, 2026, 11:20 p.m.
PD Predicate disambiguation batch_69abaff9a09c8190a81fa13f4b85bc79 completed March 7, 2026, 4:56 a.m.
Created at: March 4, 2026, 7:36 p.m.