Triple
T19636937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Perkhin |
E471421
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | House of Fabergé |
—
|
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: House of Fabergé | Statement: [Michael Perkhin, employer, House of Fabergé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: House of Fabergé Context triple: [Michael Perkhin, employer, House of Fabergé]
-
A.
House of Fabergé
chosen
The House of Fabergé was a renowned Russian jewelry firm famous for its exquisitely crafted, jewel-encrusted objets d'art, especially the imperial Easter eggs made for the Russian tsars.
-
B.
Fabergé egg
A Fabergé egg is an ornate jeweled egg created by the House of Fabergé, famed for its intricate craftsmanship and association with the Russian imperial family.
-
C.
Fabergé Limited
Fabergé Limited is a modern luxury jewelry and watch company that revives the legacy and artistic traditions of the historic House of Fabergé.
-
D.
Fabergé Inc.
Fabergé Inc. is an American personal care and cosmetics company best known for its fragrances and beauty products developed under the Fabergé brand name.
-
E.
Fabege
Fabege is a Swedish real estate company specializing in commercial properties, particularly in the Stockholm region.
- 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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641070528819085663c439f50148e |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:44 p.m.