Triple

T17017852
Position Surface form Disambiguated ID Type / Status
Subject Yeongdeungpo-gu Office E412867 entity
Predicate governingBodyType P2886 FINISHED
Object gu office
A gu office is the local administrative headquarters responsible for governing and providing public services within a district-level division in South Korea.
 E1245526 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: gu office | Statement: [Yeongdeungpo-gu Office, governingBodyType, gu office]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: gu office
Context triple: [Yeongdeungpo-gu Office, governingBodyType, gu office]
  • A. ED Office
    The ED Office is the U.S. Department of Energy’s Office of Economic Impact and Diversity, responsible for advancing equity, civil rights, and inclusive economic opportunities in the energy sector.
  • B. GOV
    GOV is the National Rail station code used to identify Govan subway station in Glasgow, Scotland.
  • C. GOV
    GOV is the IATA airport code for Gove Airport, a regional airport serving the Gove Peninsula in the Northern Territory of Australia.
  • D. GOV
    GOV is an honorific suffix used in the United Kingdom to denote a Governor, particularly in formal titles such as that of a central bank governor.
  • E. .gov
    .gov is the sponsored top-level domain primarily used by governmental entities in the United States.
  • 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: gu office
Triple: [Yeongdeungpo-gu Office, governingBodyType, gu office]
Generated description
A gu office is the local administrative headquarters responsible for governing and providing public services within a district-level division in South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: gu office
Target entity description: A gu office is the local administrative headquarters responsible for governing and providing public services within a district-level division in South Korea.
  • A. ED Office
    The ED Office is the U.S. Department of Energy’s Office of Economic Impact and Diversity, responsible for advancing equity, civil rights, and inclusive economic opportunities in the energy sector.
  • B. GOV
    GOV is the National Rail station code used to identify Govan subway station in Glasgow, Scotland.
  • C. GOV
    GOV is the IATA airport code for Gove Airport, a regional airport serving the Gove Peninsula in the Northern Territory of Australia.
  • D. GOV
    GOV is an honorific suffix used in the United Kingdom to denote a Governor, particularly in formal titles such as that of a central bank governor.
  • E. .gov
    .gov is the sponsored top-level domain primarily used by governmental entities in the United States.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d480a58c8190a3912d26debb4311 completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b4d6cb881909b64b4368fd97fa9 completed May 10, 2026, 11:57 p.m.
NEDg Description generation batch_6a011bc4617081908ad2d4c0d35fe98a completed May 10, 2026, 11:59 p.m.
NED2 Entity disambiguation (via description) batch_6a011c76d5b88190b5cda571231f5c7e completed May 11, 2026, 12:01 a.m.
Created at: April 10, 2026, 5:33 a.m.