Triple
T26747127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Narvik |
E674430
|
entity |
| Predicate | railwayLinksTo |
P109198
|
FINISHED |
| Object | Kiruna |
—
|
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: Kiruna | Statement: [Port of Narvik, railwayLinksTo, Kiruna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayLinksTo Context triple: [Port of Narvik, railwayLinksTo, Kiruna]
-
A.
railwayConnectsTo
chosen
Indicates that one railway line, track, or network is directly linked or joined to another, allowing trains to move between them.
-
B.
countryRailConnection
Indicates that there is a railway connection or service linking two countries.
-
C.
providesRailConnectionsWithin
Indicates that an entity offers or facilitates rail transport links connecting locations inside a specified area or region.
-
D.
relatedRailroad
Indicates that there is an association or connection between an entity and a specific railroad, such as ownership, operation, service, or historical linkage.
-
E.
connectsToRailStation
Indicates that one entity has a direct link, route, or access connection to a rail station.
- 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_69eecda63a3881908095c47900692e65 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 3:52 a.m.