Triple
T9045965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mirror |
E216755
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Lyudmila Feiginova |
E775019
|
NE FINISHED |
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: Lyudmila Feiginova | Statement: [Mirror, editor, Lyudmila Feiginova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyudmila Feiginova Context triple: [Mirror, editor, Lyudmila Feiginova]
-
A.
Lyudmila Feiginova
chosen
Lyudmila Feiginova is a Soviet film editor best known for her work on Sergei Bondarchuk’s epic adaptation of Leo Tolstoy’s "War and Peace" (1965–1967).
-
B.
Anna Vasilchikova
Anna Vasilchikova was a Russian noblewoman who became one of the later wives of Tsar Ivan IV "the Terrible" of Russia.
-
C.
Ulyana Lopatkina
Ulyana Lopatkina is a renowned Russian ballerina celebrated as one of the leading principal dancers of her generation at the Mariinsky Ballet.
-
D.
Svetlana Svetlichnaya
Svetlana Svetlichnaya is a Soviet and Russian actress best known for her glamorous and seductive roles in classic Soviet cinema.
-
E.
Galina Kulik
Galina Kulik is a person notable enough to be recognized as a bearer of the surname Kulik, though specific widely known public details about her are not readily available.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b4e4b888190a425e29b193b506f |
completed | April 1, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d316e50b548190b5f90a9753ad7cb0 |
completed | April 6, 2026, 2:13 a.m. |
Created at: March 30, 2026, 7:09 p.m.