Triple

T7217834
Position Surface form Disambiguated ID Type / Status
Subject Keimyung University E150180 entity
Predicate hasCampus P116 FINISHED
Object Seongseo Campus E690348 NE FINISHED

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: Seongseo Campus | Statement: [Keimyung University, hasCampus, Seongseo Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seongseo Campus
Context triple: [Keimyung University, hasCampus, Seongseo Campus]
  • A. Hwasun Campus
    Hwasun Campus is a satellite campus of Chonnam National University located in Hwasun, South Korea, supporting specialized education and research facilities.
  • B. Daemyeong Campus chosen
    Daemyeong Campus is one of the main campuses of Keimyung University in Daegu, South Korea, housing various academic and student facilities.
  • C. Sinchon Campus
    Sinchon Campus is Yonsei University's main urban campus in Seoul, known for its vibrant student life and central role in the university's academic and cultural activities.
  • D. Sangju campus
    Sangju campus is a regional campus of Kyungpook National University in South Korea, focusing on agriculture, life sciences, and related disciplines.
  • E. Sejong Campus
    Sejong Campus is Korea University's satellite campus located in Sejong City, offering a range of undergraduate and graduate programs with a focus on public policy, science, and technology.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c687effb44819092b95d07d0368c9f completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e99170d88190b1aef326a7d81134 completed March 27, 2026, 8:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c934c199f08190a8fbb7f3c6f5464c completed March 29, 2026, 2:18 p.m.
Created at: March 27, 2026, 2:53 p.m.