Triple
T19425951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaminsky |
E485979
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Kaminski |
—
|
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: Kaminski | Statement: [Kaminsky, hasVariant, Kaminski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaminski Context triple: [Kaminsky, hasVariant, Kaminski]
-
A.
Kamiński
chosen
Kamiński is a common Polish surname borne by numerous notable figures in fields such as film, sports, and politics.
-
B.
Kaminsky
Kaminsky is the original family surname of American entertainer Danny Kaye, born David Daniel Kaminsky.
-
C.
Kosinski
Kosinski is a surname most prominently associated with American film director Joseph Kosinski, known for visually striking action and science-fiction movies.
-
D.
Karski
Karski is a Polish surname most famously borne by Jan Karski, the World War II resistance courier who reported on the Holocaust to the Allies.
-
E.
Herling-Grudziński
Herling-Grudziński is the surname of Gustaw Herling-Grudziński, a prominent Polish writer and dissident known for his accounts of Soviet labor camps.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63218772c8190a48b6cb01bd12b73 |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.