Triple
T21703427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bohuslän |
E535711
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Lysekil |
—
|
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: Lysekil | Statement: [Bohuslän, containsCity, Lysekil]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lysekil Context triple: [Bohuslän, containsCity, Lysekil]
-
A.
Lysekil
chosen
Lysekil is a coastal town in western Sweden known for its picturesque archipelago, fishing heritage, and popular seaside tourism.
-
B.
Hässleholm
Hässleholm is a town in southern Sweden’s Skåne County known as a regional railway hub and service center.
-
C.
Härnösand
Härnösand is a coastal city in northern Sweden known for its historic architecture, maritime heritage, and role as an administrative and cultural center in the region.
-
D.
Hudiksvall
Hudiksvall is a coastal town in east-central Sweden known for its historic wooden buildings and harbor on the Gulf of Bothnia.
-
E.
Hammarö
Hammarö is a Swedish island and municipality in Värmland County, known for its forests, coastline, and proximity to the city of Karlstad.
- 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_69e0c46b44c0819088ab883ebd44e0e8 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef9b82901c81909de242c920fbc164 |
completed | April 27, 2026, 5:23 p.m. |
Created at: April 16, 2026, 6:46 p.m.