Triple
T17339216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lærdal Tunnel |
E421020
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Lærdal |
—
|
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: Lærdal | Statement: [Lærdal Tunnel, connects, Lærdal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lærdal Context triple: [Lærdal Tunnel, connects, Lærdal]
-
A.
Lærdal
chosen
Lærdal is a municipality in Vestland county, Norway, known for its dramatic fjord landscapes, historic wooden architecture, and the UNESCO-listed Nærøyfjord area nearby.
-
B.
Sogndalsdalen
Sogndalsdalen is a scenic valley in western Norway known for its dramatic landscapes, rivers, and access to hiking and outdoor activities.
-
C.
Groruddalen
Groruddalen is a large valley and suburban area in the northeastern part of Oslo, Norway, known for its diverse population and extensive residential neighborhoods.
-
D.
Hattfjelldal
Hattfjelldal is a sparsely populated municipality in Nordland county, Norway, known for its mountainous terrain, extensive wilderness areas, and strong Sami cultural heritage.
-
E.
Gravdal
Gravdal is a small coastal village on the island of Vestvågøy in Norway’s Lofoten archipelago.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a14ec90819098db2ac0d58a53e1 |
completed | April 19, 2026, 2:12 a.m. |
Created at: April 10, 2026, 5:44 a.m.