Triple
T27912421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norwegian National Road 39 |
E705967
|
entity |
| Predicate | connectsCoastalTowns |
P66192
|
FINISHED |
| Object | yes |
—
|
LITERAL FINISHED |
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: yes | Statement: [Norwegian National Road 39, connectsCoastalTowns, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsCoastalTowns Context triple: [Norwegian National Road 39, connectsCoastalTowns, yes]
-
A.
connectsCoastalCity
chosen
Indicates a relationship where one entity provides a direct connection or link (such as transport or infrastructure) between coastal cities.
-
B.
connectsCoastToBorder
Indicates a relationship where something (such as a route, feature, or boundary) links a coastal area directly to a national or regional border.
-
C.
connectsCoastToInland
Indicates a relationship where something (such as a route, structure, or feature) links a coastal area to an inland area.
-
D.
includesCoastalTown
Indicates that a geographic area or region contains at least one town located on or directly adjacent to a coastline.
-
E.
connectsToCoastTown
Indicates that one location has a direct connection or route leading to a town situated on the coast.
- 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_69ef96b5aad08190be36a277c31e7004 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fd05ba6b2c81909c62b46237d10365 |
completed | May 7, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69fd03039e48819082b6e12c5453885a |
completed | May 7, 2026, 9:24 p.m. |
Created at: April 27, 2026, 6:51 p.m.