Triple
T19219127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johan Anders Larsson |
E480563
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Larsson |
—
|
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: Larsson | Statement: [Johan Anders Larsson, familyName, Larsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larsson Context triple: [Johan Anders Larsson, familyName, Larsson]
-
A.
Larsson
chosen
Larsson is a common Swedish surname borne by numerous notable individuals across fields such as literature, music, and sports.
-
B.
Larson
Larson is a common surname of Scandinavian origin, meaning "son of Lars."
-
C.
Larssons
"Larssons" is a notable work by Swedish painter Carl Larsson, likely one of his illustrated books or collections depicting family life and Swedish domestic interiors.
-
D.
Jansson
Jansson is a Finnish surname most famously borne by Tove Jansson, the creator of the Moomin series.
-
E.
Lundh
Lundh is a variant form of the Scandinavian surname Lund, which is associated with families originating from regions such as Sweden and Denmark.
- 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa3d5684819092d3083f65ea90d5 |
completed | April 20, 2026, 10:04 a.m. |
Created at: April 10, 2026, 1:23 p.m.