Triple

T16535404
Position Surface form Disambiguated ID Type / Status
Subject Suwon E401676 entity
Predicate hasUniversity P113 FINISHED
Object Suwon University NE NERFINISHED

How this triple was built (2 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: Suwon University | Statement: [Suwon, hasUniversity, Suwon University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suwon University
Context triple: [Suwon, hasUniversity, Suwon University]
  • A. Sungkyul University
    Sungkyul University is a South Korean higher education institution known for producing alumni such as actor Wi Ha-joon.
  • B. Dongguk University
    Dongguk University is a prominent private university in South Korea known for its Buddhist foundation and strong programs in the humanities, arts, and social sciences.
  • C. Hansung University
    Hansung University is a private higher education institution in Seoul, South Korea, known for its programs in humanities, social sciences, design, and information technology.
  • D. Kyungsung University
    Kyungsung University is a private higher education institution located in Busan, South Korea, known for its programs in humanities, social sciences, arts, and media.
  • E. Kyonggi University chosen
    Kyonggi University is a private South Korean university known for its main campus in Suwon and a broad range of undergraduate and graduate programs.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e345574d88819094548367bf983078 completed April 18, 2026, 8:48 a.m.
Created at: April 10, 2026, 5:15 a.m.