Triple
T20628708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivar Kreuger |
E506889
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Swedish Match |
—
|
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: Swedish Match | Statement: [Ivar Kreuger, founded, Swedish Match]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swedish Match Context triple: [Ivar Kreuger, founded, Swedish Match]
-
A.
Swedish Match AB
chosen
Swedish Match AB is a Swedish company best known for producing smokeless tobacco products such as snus, as well as matches and lighters, for markets worldwide.
-
B.
Swarovski
Swarovski is an Austrian luxury brand renowned worldwide for its precision-cut crystal jewelry, figurines, and decorative items.
-
C.
Hansnes
Hansnes is a small coastal village in northern Norway that serves as an administrative and ferry hub for the surrounding islands in Troms.
-
D.
Wahlström & Widstrand
Wahlström & Widstrand is a prominent Swedish publishing house known for literary fiction and non-fiction, and is part of the Bonnier media conglomerate.
-
E.
Mondelange
Mondelange is a commune in northeastern France’s Moselle department, known for its location in the Grand Est region near the Luxembourg border.
- 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_69e0b4bd4a0081908d4e97a590a33fb2 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe771e88190a48471bf83b4804d |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.