Triple
T27425701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sotetsu Railway |
E690477
|
entity |
| Predicate | throughServiceViaLine |
P66391
|
FINISHED |
| Object | Sotetsu–Tokyu Link Line |
—
|
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: Sotetsu–Tokyu Link Line | Statement: [Sotetsu Railway, throughServiceViaLine, Sotetsu–Tokyu Link Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: throughServiceViaLine Context triple: [Sotetsu Railway, throughServiceViaLine, Sotetsu–Tokyu Link Line]
-
A.
throughServiceToLine
chosen
Indicates that a service operates through or along a specified line, establishing a through-service relationship between the service and the line.
-
B.
lineServed
Indicates that a particular transportation line (such as a bus, train, or metro line) provides service to or is operated at a given stop, station, or route segment.
-
C.
servesLineTo
Indicates that one entity provides or operates a particular service line or route for another entity or location.
-
D.
servedByLine
Indicates that a transportation stop, station, or location is provided service by a specific transit line.
-
E.
formerLineServed
Indicates that a particular transit line previously provided service to a route, station, or area but no longer does so.
- 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_69ef52003fb48190b0f1295246182a86 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62d546b2881909d0acb99ce291de1 |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 12:40 p.m.