Triple
T17339431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romerike |
E421025
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Eidsvoll |
—
|
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: Eidsvoll | Statement: [Romerike, contains, Eidsvoll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eidsvoll Context triple: [Romerike, contains, Eidsvoll]
-
A.
Eidsvoll
chosen
Eidsvoll is a historic Norwegian town best known as the site where Norway’s constitution was drafted and signed in 1814.
-
B.
Akershus
Akershus is a historical county in southeastern Norway that encompassed areas around the capital Oslo and played a key role in the region’s administrative and military history.
-
C.
Eidsvolls plass
Eidsvolls plass is a central public square and park in Oslo, Norway, located in front of the Parliament building and often used for gatherings and events.
-
D.
Fredrikstad
Fredrikstad is a coastal city in southeastern Norway known for its well-preserved fortified old town and role as a regional educational and commercial center.
-
E.
Rakkestad
Rakkestad is a rural municipality in Viken county, southeastern Norway, known for its agriculture and forests.
- 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.