Triple
T28421975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yotsubashi Station |
E719962
|
entity |
| Predicate | hasConnectionByWalk |
P90518
|
FINISHED |
| Object | Shinsaibashi Station |
—
|
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: Shinsaibashi Station | Statement: [Yotsubashi Station, hasConnectionByWalk, Shinsaibashi Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConnectionByWalk Context triple: [Yotsubashi Station, hasConnectionByWalk, Shinsaibashi Station]
-
A.
hasWalkingRouteConnection
chosen
Indicates that there is a walkable path or route directly connecting two locations.
-
B.
hasTrailConnection
Indicates that one location is connected to another by a traversable trail or path.
-
C.
hasConnection
Indicates that there exists a link, association, or relationship between two entities.
-
D.
hasWorldMapConnectionTo
Indicates that one location is directly connected to another on a world map, such as by a route, link, or navigable path.
-
E.
hasSummitConnectionTo
Indicates a relationship where two entities are connected through a shared summit, peak, or highest point, such that one has a direct summit-related linkage to the other.
- 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_69eff6f1c5088190bc24bfbf92f9c017 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69ffa5f31c8881908c26e2aa52df6ece |
completed | May 9, 2026, 9:24 p.m. |
| PD | Predicate disambiguation | batch_69ffa42aee408190ad1a5f285688b338 |
completed | May 9, 2026, 9:16 p.m. |
Created at: April 28, 2026, 1:34 a.m.