Triple
T1149304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akershus Fortress |
E23638
|
entity |
| Predicate | overlooks |
P1323
|
FINISHED |
| Object | Oslofjord |
E33322
|
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: Oslofjord | Statement: [Akershus Fortress, overlooks, Oslofjord]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oslofjord Context triple: [Akershus Fortress, overlooks, Oslofjord]
-
A.
Oslofjord
chosen
Oslofjord is a large inlet in southeastern Norway known for its islands, coastal towns, and role as the maritime gateway to Oslo.
-
B.
Sognefjord
Sognefjord is Norway’s longest and deepest fjord, renowned for its dramatic cliffs, glacial landscapes, and scenic coastal villages.
-
C.
Lysefjord
Lysefjord is a dramatic, steep-walled fjord in southwestern Norway, famed for its towering cliffs, including the iconic Preikestolen (Pulpit Rock), and striking natural scenery.
-
D.
Norsjø
Norsjø is a large lake in Telemark, Eastern Norway, known as an important part of the Telemark Canal waterway system.
-
E.
Trondheimsfjord
Trondheimsfjord is a major Norwegian fjord on the central coast, known for its deep waters, rich marine life, and the city of Trondheim along its shores.
- 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_69a493f0d32c8190ac74bad3c87f2641 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc7190308190ab104480ed208b22 |
completed | March 1, 2026, 10:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acb2f3df34819090d942aad0a409fa |
completed | March 7, 2026, 11:21 p.m. |
Created at: March 1, 2026, 7:44 p.m.