Triple
T25124633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bergen Light Rail |
E629362
|
entity |
| Predicate | fyllingsdalenSectionOpened |
P80433
|
FINISHED |
| Object | 2022-11-21 |
—
|
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: 2022-11-21 | Statement: [Bergen Light Rail, fyllingsdalenSectionOpened, 2022-11-21]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fyllingsdalenSectionOpened Context triple: [Bergen Light Rail, fyllingsdalenSectionOpened, 2022-11-21]
-
A.
sectionOpened
chosen
Indicates that a particular section has been opened or expanded, making its contents visible or active.
-
B.
valleyOpensToward
Indicates that a valley is oriented or slopes in the direction of a specified location or feature, effectively opening toward it.
-
C.
parkSectionOpening
Indicates that a specific section of a park is opening or becoming available for use, typically at a particular time or under certain conditions.
-
D.
isInFylke
Indicates that one entity (typically a place or municipality) is located within a specific Norwegian county (fylke).
-
E.
scenicSectionName
Indicates the specific name assigned to a scenic section or segment within a larger route, area, or context.
- 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_69e2ff3288048190bd82c3b7f7bd0e62 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f465cf077c819091cdefb28f4a35d2 |
completed | May 1, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:28 a.m.