Triple
T8095660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Busan Catholic University |
E188977
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Yeongnam |
E29096
|
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: Yeongnam | Statement: [Busan Catholic University, region, Yeongnam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yeongnam Context triple: [Busan Catholic University, region, Yeongnam]
-
A.
Gyeongbuk
Gyeongbuk is a province in eastern South Korea known for its historical sites, cultural heritage, and scenic rural landscapes.
-
B.
Anseongcheon
Anseongcheon is a river in South Korea that flows through the city of Pyeongtaek in Gyeonggi Province.
-
C.
Minho region
The Minho region is a historic and culturally rich area in northwest Portugal, known for its lush green landscapes, traditional cuisine, and production of Vinho Verde wine.
-
D.
Yeongnam region
chosen
The Yeongnam region is a major southeastern area of South Korea encompassing key cities such as Busan and Daegu, known for its dense population, industry, and distinct cultural identity.
-
E.
Myeongneung
Myeongneung is one of the royal burial sites from Korea’s Joseon Dynasty, forming part of the UNESCO-listed Royal Tombs complex.
- 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_69ca82b886d88190a9cba0d5a4a27521 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4291f1d4819098985ac2b20b6c75 |
completed | March 31, 2026, 3:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd3438ae2481909549a05f195cda39 |
completed | April 1, 2026, 3:05 p.m. |
Created at: March 30, 2026, 5:30 p.m.