Triple

T23408028
Position Surface form Disambiguated ID Type / Status
Subject Hamhung E559987 entity
Predicate hasEducationalInstitution P113 FINISHED
Object Hamhung University of Education NE NERFINISHED

How this triple was built (3 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: Hamhung University of Education | Statement: [Hamhung, hasEducationalInstitution, Hamhung University of Education]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hamhung University of Education
Context triple: [Hamhung, hasEducationalInstitution, Hamhung University of Education]
  • A. Korea National University of Education
    Korea National University of Education is a specialized national institution in South Korea dedicated to training and educating future teachers and education professionals.
  • B. Tongmyong University
    Tongmyong University is a higher education institution located in Busan, South Korea, offering a range of undergraduate and graduate programs.
  • C. Busan National University of Education
    Busan National University of Education is a specialized public institution in Busan, South Korea, dedicated primarily to training future elementary school teachers and educational professionals.
  • D. Hanbat National University
    Hanbat National University is a public university in South Korea known for its strong engineering, technology, and design programs.
  • E. Hanseo University
    Hanseo University is a private South Korean university known for its specialized programs in fields such as aviation, health sciences, and arts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hamhung University of Education
Target entity description: Hamhung University of Education is a higher education institution in Hamhung, North Korea, specializing in training teachers and educational professionals.
  • A. Korea National University of Education
    Korea National University of Education is a specialized national institution in South Korea dedicated to training and educating future teachers and education professionals.
  • B. Tongmyong University
    Tongmyong University is a higher education institution located in Busan, South Korea, offering a range of undergraduate and graduate programs.
  • C. Busan National University of Education
    Busan National University of Education is a specialized public institution in Busan, South Korea, dedicated primarily to training future elementary school teachers and educational professionals.
  • D. Hanbat National University
    Hanbat National University is a public university in South Korea known for its strong engineering, technology, and design programs.
  • E. Hanseo University
    Hanseo University is a private South Korean university known for its specialized programs in fields such as aviation, health sciences, and arts.
  • F. None of above. chosen

Provenance (2 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_69e2454b3a5881909c64773dc8a5d289 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a50f3f90819084fb682597fee1e1 completed April 29, 2026, 6:28 a.m.
Created at: April 17, 2026, 5:38 p.m.