Triple
T18432702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erik Karlsson |
E450311
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Karlsson |
—
|
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: Karlsson | Statement: [Erik Karlsson, familyName, Karlsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karlsson Context triple: [Erik Karlsson, familyName, Karlsson]
-
A.
Karlsson
chosen
Karlsson is a Scandinavian variant of the surname Carlson, commonly found in Sweden and other Nordic countries.
-
B.
Karl Karlsson
Karl Karlsson is the birth name of Charles XI, who was King of Sweden from 1660 to 1697 and a key consolidator of royal power in the Swedish Empire.
-
C.
Nils
Nils is a Scandinavian male given name, commonly used in countries like Norway and Sweden and derived from the name Nicholas.
-
D.
Kasper
Kasper is a surname most notably associated with former American football wide receiver Kevin Kasper.
-
E.
Moominpappa
Moominpappa is a thoughtful, adventurous, and somewhat nostalgic father figure in Tove Jansson’s Moomin series, known for his memoir-writing and love of seafaring.
- 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_69d8d381d6388190a9e94e9c658174e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51b183adc8190987bc7749d0e673c |
completed | April 19, 2026, 6:12 p.m. |
Created at: April 10, 2026, 11:27 a.m.