Triple
T16984384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biwa-ko Line |
E412024
|
entity |
| Predicate | railwayCompanyBrandName |
P39149
|
FINISHED |
| Object | Biwa-ko 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: Biwa-ko Line | Statement: [Biwa-ko Line, railwayCompanyBrandName, Biwa-ko Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayCompanyBrandName Context triple: [Biwa-ko Line, railwayCompanyBrandName, Biwa-ko Line]
-
A.
railwayCompany
Indicates that one entity is a railway company that owns, operates, or manages railway services or infrastructure in relation to another entity.
-
B.
railwayCompanyType
Indicates the specific category or classification of a railway company in terms of its role, ownership, or operational type.
-
C.
notableTrainBrand
Indicates that an entity is a well-known or significant brand associated with trains or railway services.
-
D.
railwayOperatorBranding
chosen
Indicates that one entity is responsible for the railway-related branding, livery, or visual identity applied to another entity (such as a train service, station, or rolling stock).
-
E.
railwayCompanyOnRoute
Indicates that a particular railway company operates or provides service on a specified route.
- 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d18a0bf881908c449f499eb86495 |
completed | April 18, 2026, 6:46 p.m. |
| PD | Predicate disambiguation | batch_69e35d4dff4881909b384e30f2d36bff |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.