Triple
T6015989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muskö |
E133949
|
entity |
| Predicate | hasRoadLink |
P11435
|
FINISHED |
| Object | Muskö Tunnel |
E561236
|
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: Muskö Tunnel | Statement: [Muskö, hasRoadLink, Muskö Tunnel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Muskö Tunnel Context triple: [Muskö, hasRoadLink, Muskö Tunnel]
-
A.
Muskö Tunnel
chosen
Muskö Tunnel is a Swedish underwater road tunnel connecting the island of Muskö to the mainland, notable for serving the strategic Muskö naval base.
-
B.
Lærdal Tunnel
The Lærdal Tunnel is a 24.5-kilometer road tunnel in Norway, renowned as one of the world's longest road tunnels and a key link between Oslo and Bergen.
-
C.
Maastunnel
Maastunnel is a historic traffic tunnel in Rotterdam, the Netherlands, carrying road, bicycle, and pedestrian traffic beneath the Nieuwe Maas river.
-
D.
Tromsøysund Tunnel
Tromsøysund Tunnel is an undersea road tunnel in northern Norway that connects the island city of Tromsø to the mainland.
-
E.
Bømlafjord Tunnel
Bømlafjord Tunnel is a subsea road tunnel in Vestland county, Norway, forming part of the fixed link connection between the island municipality of Bømlo and the mainland.
- 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_69c0087361a48190905c6b55969852b8 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f82dd688190ad8882d8fb547cb5 |
completed | March 22, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1136a4720819092bf2c6a9101c71b |
completed | March 23, 2026, 10:18 a.m. |
Created at: March 22, 2026, 4:06 p.m.