Triple
T5351330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Selma Lagerlöf |
E102583
|
entity |
| Predicate | workLocation |
P7
|
FINISHED |
| Object | Mårbacka |
E513987
|
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: Mårbacka | Statement: [Selma Lagerlöf, workLocation, Mårbacka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mårbacka Context triple: [Selma Lagerlöf, workLocation, Mårbacka]
-
A.
Mårbacka
chosen
Mårbacka is the historic family estate and later home of Swedish author and Nobel laureate Selma Lagerlöf, now preserved as a museum in Värmland, Sweden.
-
B.
Mönsterås
Mönsterås is a small coastal town and municipality in Kalmar County, southeastern Sweden, known for its Baltic Sea shoreline and traditional Swedish countryside.
-
C.
Fjällbacka
Fjällbacka is a picturesque coastal village in western Sweden, known for its fishing heritage, granite cliffs, and as the setting of Camilla Läckberg’s crime novels.
-
D.
Skarpäng
Skarpäng is a residential urban area within Täby Municipality in Stockholm County, Sweden.
-
E.
Östhammar
Östhammar is a small coastal town and municipality in eastern Sweden known for its archipelago, historic wooden buildings, and proximity to the Forsmark nuclear power plant.
- 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_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd861188ac81908ef2b1f25cc6c864 |
completed | March 20, 2026, 5:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf33395b248190a1552288a3d5213c |
completed | March 22, 2026, 12:09 a.m. |
Created at: March 20, 2026, 2:01 p.m.