Triple
T30785831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 広島市現代美術館 |
E783951
|
entity |
| Predicate | 最寄交通機関 |
P3791
|
FINISHED |
| Object | 広島電鉄皆実線 |
—
|
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: 広島電鉄皆実線 | Statement: [広島市現代美術館, 最寄交通機関, 広島電鉄皆実線]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 最寄交通機関 Context triple: [広島市現代美術館, 最寄交通機関, 広島電鉄皆実線]
-
A.
最寄り在来線駅
Indicates the relationship where a given location is associated with its nearest conventional (non-high-speed) railway station.
-
B.
nearestShinkansenStation
Indicates that one entity is the Shinkansen (bullet train) station geographically closest to the other entity.
-
C.
nearestMajorTransportHub
Indicates that one location is the closest significant transportation center (such as a major train station, airport, or bus terminal) to another location.
-
D.
formerTerminalStation
Indicates that a location once served as the end point (terminus) of a transportation line or route but no longer holds that status.
-
E.
hasPublicTransportConnection
chosen
Indicates that there is an available public transportation link or service connecting the related entities.
- 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_69f224b213c8819083886073f90b647e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68fe8168c8190b083be0e33988b9c |
completed | May 2, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:41 p.m.