Triple
T12614565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 北海道大学水産学部 |
E301218
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | 北海道大学 |
E10012
|
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: 北海道大学 | Statement: [北海道大学水産学部, partOf, 北海道大学]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 北海道大学 Context triple: [北海道大学水産学部, partOf, 北海道大学]
-
A.
Hokkaido University
chosen
Hokkaido University is a major national research university in Sapporo, Japan, known for its broad academic offerings, strong science and agriculture programs, and spacious, park-like campus.
-
B.
東北大学
東北大学は、日本の宮城県仙台市に本部を置く、研究力と工学・理学分野で特に高い評価を受ける国立総合大学です。
-
C.
Tohoku University
Tohoku University is a prestigious national research university in Sendai, Japan, renowned for its strong science and engineering programs and pioneering admission of women and international students.
-
D.
北海道大学水産学部
北海道大学水産学部 is the fisheries sciences faculty of Hokkaido University, specializing in marine science, fisheries, and related environmental and resource studies.
-
E.
京都帝国大学
京都帝国大学 was a major prewar Japanese imperial university in Kyoto that later became Kyoto University, renowned for its research and academic excellence.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c4f5b48190af76414ef678ba7c |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ed2e12c819097cfd2a40116f491 |
completed | May 2, 2026, 8:30 p.m. |
Created at: April 9, 2026, 5:12 p.m.