Triple
T15021256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saltstraumen maelstrom |
E378088
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Saltfjorden |
E1212560
|
NE 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: Saltfjorden | Statement: [Saltstraumen maelstrom, connects, Saltfjorden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saltfjorden Context triple: [Saltstraumen maelstrom, connects, Saltfjorden]
-
A.
Saltfjorden
chosen
Saltfjorden is a coastal fjord in Nordland county, Norway, known for containing the powerful Saltstraumen tidal maelstrom.
-
B.
Langfjorden
Langfjorden is a notable fjord in Norway’s Møre og Romsdal county, characterized by its deep waters and steep surrounding mountains.
-
C.
Nachvak Fjord
Nachvak Fjord is a remote, steep-walled glacial fjord on the northern coast of Labrador in Canada, known for its dramatic Arctic landscapes and rugged wilderness.
-
D.
Sandviksfjorden
Sandviksfjorden is a celebrated 19th-century Norwegian landscape painting by Hans Gude, depicting a coastal fjord scene with detailed maritime and atmospheric effects.
-
E.
Saudafjorden
Saudafjorden is a narrow, scenic fjord in Rogaland county, southwestern Norway, known for its steep mountainsides and industrial town of Sauda at its inner end.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded765462c819097f331c9b39c80e3 |
completed | April 15, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004568c93c81908450887f72de8466 |
completed | May 10, 2026, 8:44 a.m. |
Created at: April 10, 2026, 2:56 a.m.