Triple
T9806082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 京都大学宇治キャンパス |
E237956
|
entity |
| Predicate | hasCampusColor |
P2465
|
FINISHED |
| Object | 緑地が多いキャンパス |
—
|
LITERAL 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: 緑地が多いキャンパス | Statement: [京都大学宇治キャンパス, hasCampusColor, 緑地が多いキャンパス]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCampusColor Context triple: [京都大学宇治キャンパス, hasCampusColor, 緑地が多いキャンパス]
-
A.
hasCampusOn
Indicates that an institution or organization maintains a campus located on a specified geographic area or site.
-
B.
hasSchoolColours
Indicates that an entity is associated with one or more official colours that represent it, typically in formal or symbolic contexts.
-
C.
hasCampusCity
Indicates that an educational institution or campus is located in a particular city.
-
D.
hasCampusFeature
chosen
Indicates that a campus possesses or includes a specific physical or functional feature.
-
E.
hasCollegeCampus
Indicates that an institution or organization possesses or is associated with a specific college campus as a physical or organizational site.
- F. None of above.
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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7b67748190ba16ce868f29d13e |
completed | April 1, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.