Triple
T20648026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crown Princess Märtha of Norway |
E507408
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Skaugum |
—
|
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: Skaugum | Statement: [Crown Princess Märtha of Norway, residence, Skaugum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skaugum Context triple: [Crown Princess Märtha of Norway, residence, Skaugum]
-
A.
Skaugum
chosen
Skaugum is the official country residence of the Norwegian royal family, located in Asker near Oslo.
-
B.
Skaaren
Skaaren is a surname most notably associated with Warren Skaaren, an American screenwriter and film producer.
-
C.
Sköndal
Sköndal is a residential district in southern Stockholm, Sweden, known for its green areas and proximity to lakes.
-
D.
Skage
Skage is a small village in the municipality of Overhalla in Trøndelag county, Norway.
-
E.
Laukvik
Laukvik is a small coastal village in northern Norway, located in the Lofoten archipelago and known for its scenic Arctic landscapes and fishing heritage.
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af1fbfa881908a5b9db143e362d0 |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.