Triple
T22864885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christian Krohg |
E567023
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Per Krohg |
—
|
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: Per Krohg | Statement: [Christian Krohg, child, Per Krohg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Per Krohg Context triple: [Christian Krohg, child, Per Krohg]
-
A.
Per Krohg
chosen
Per Krohg was a Norwegian painter and muralist best known for his large-scale public works, including the mural in the United Nations Security Council Chamber.
-
B.
Christian Krohg
Christian Krohg was a prominent Norwegian naturalist painter, illustrator, author, and journalist known for his socially engaged depictions of everyday life in the late 19th and early 20th centuries.
-
C.
Oda Krohg
Oda Krohg was a Norwegian painter and central figure in the bohemian art and literary circles of late 19th-century Kristiania (Oslo).
-
D.
Peder Balke
Peder Balke was a 19th-century Norwegian painter known for his dramatic, atmospheric landscapes of the Nordic coast and wilderness.
-
E.
Frits Thaulow
Frits Thaulow was a Norwegian Impressionist painter renowned for his atmospheric landscapes and masterful depictions of water and rural scenes.
- 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17effd93081909f2c9a8857a8728b |
completed | April 29, 2026, 3:46 a.m. |
Created at: April 17, 2026, 3:38 p.m.