Triple

T15859041
Position Surface form Disambiguated ID Type / Status
Subject 경기도 김포시 E384532 entity
Predicate governingBody P46 FINISHED
Object 김포시청
김포시청은 경기도 김포시의 행정과 지방자치 업무를 총괄하는 기초자치단체 청사이다.
 E1180005 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: 김포시청 | Statement: [경기도 김포시, governingBody, 김포시청]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 김포시청
Context triple: [경기도 김포시, governingBody, 김포시청]
  • A. Pusanjin-gu Office
    Pusanjin-gu Office is the local government administrative headquarters responsible for managing public services and municipal affairs in Pusanjin District of Busan, South Korea.
  • B. Incheon City Hall
    Incheon City Hall is the main administrative and governmental headquarters of the metropolitan city of Incheon, South Korea.
  • C. Suwon City Hall
    Suwon City Hall is the main municipal government building and administrative center serving the city of Suwon in South Korea.
  • D. Seongbuk-gu Office
    Seongbuk-gu Office is the main local government building and administrative headquarters serving Seoul’s Seongbuk District.
  • E. Cijin District Office
    Cijin District Office is the local government authority responsible for administering public services and municipal affairs in Cijin District, Kaohsiung, Taiwan.
  • 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: 김포시청
Triple: [경기도 김포시, governingBody, 김포시청]
Generated description
김포시청은 경기도 김포시의 행정과 지방자치 업무를 총괄하는 기초자치단체 청사이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 김포시청
Target entity description: 김포시청은 경기도 김포시의 행정과 지방자치 업무를 총괄하는 기초자치단체 청사이다.
  • A. Pusanjin-gu Office
    Pusanjin-gu Office is the local government administrative headquarters responsible for managing public services and municipal affairs in Pusanjin District of Busan, South Korea.
  • B. Incheon City Hall
    Incheon City Hall is the main administrative and governmental headquarters of the metropolitan city of Incheon, South Korea.
  • C. Suwon City Hall
    Suwon City Hall is the main municipal government building and administrative center serving the city of Suwon in South Korea.
  • D. Seongbuk-gu Office
    Seongbuk-gu Office is the main local government building and administrative headquarters serving Seoul’s Seongbuk District.
  • E. Cijin District Office
    Cijin District Office is the local government authority responsible for administering public services and municipal affairs in Cijin District, Kaohsiung, Taiwan.
  • 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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1555956ec8190b13602a177e7a2bb completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa14da7ac8190bbef49a1602a76fe completed May 9, 2026, 9:04 p.m.
NEDg Description generation batch_69ffa41b33cc819096553ee33b144d36 completed May 9, 2026, 9:16 p.m.
NED2 Entity disambiguation (via description) batch_69ffa4a168108190b6edf41830aa4cd0 completed May 9, 2026, 9:18 p.m.
Created at: April 10, 2026, 4:50 a.m.