Triple
T21945407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fredrik Backman |
E541920
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Fredrik Backman |
—
|
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: Fredrik Backman | Statement: [Fredrik Backman, name, Fredrik Backman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fredrik Backman Context triple: [Fredrik Backman, name, Fredrik Backman]
-
A.
Fredrik Backman
chosen
Fredrik Backman is a Swedish author best known for his bestselling novel "A Man Called Ove" and other character-driven contemporary fiction works.
-
B.
Per Petterson
Per Petterson is a Norwegian novelist acclaimed for his quietly powerful, introspective fiction, including the international success "Out Stealing Horses."
-
C.
Klara Sjö
Klara Sjö is a narrow canal-like body of water in central Stockholm that forms part of the city's inner waterways.
-
D.
Anneli Jordahl
Anneli Jordahl is a Swedish author and literary critic known for her socially engaged novels and essays, often focusing on class, gender, and cultural issues.
-
E.
Tobias Moers
Tobias Moers is a German automotive executive best known for leading Mercedes-AMG before becoming CEO of luxury sports car maker Aston Martin Lagonda.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12427c2b48190949c41bd3be2d9f3 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:56 p.m.