Triple
T13969987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villanelle |
E336031
|
entity |
| Predicate | realNameInStory |
P9233
|
FINISHED |
| Object | Oksana Astankova |
E336620
|
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: Oksana Astankova | Statement: [Villanelle, realNameInStory, Oksana Astankova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oksana Astankova Context triple: [Villanelle, realNameInStory, Oksana Astankova]
-
A.
Oksana Astankova
chosen
Oksana Astankova is a charismatic and unpredictable Russian assassin, better known as Villanelle, from the television series "Killing Eve."
-
B.
Yevgeniya Makhankova
Yevgeniya Makhankova is a Soviet film editor best known for her work on the classic 1977 romantic comedy "Office Romance."
-
C.
Veronika Ozerova
Veronika Ozerova is an actress known for appearing in the science fiction war film "The Darkest Hour."
-
D.
Anna Vasilchikova
Anna Vasilchikova was a Russian noblewoman who became one of the later wives of Tsar Ivan IV "the Terrible" of Russia.
-
E.
Elena Larionova
Elena Larionova is known as the wife of Russian Hall of Fame ice hockey player Igor Larionov.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e8daeac8190aadd4b3b60222482 |
completed | April 14, 2026, 12:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac90250881908f1945793d261752 |
completed | May 6, 2026, 9:03 p.m. |
Created at: April 9, 2026, 10:18 p.m.