Triple
T22794348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalya Bondarchuk |
E564200
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bondarchuk |
—
|
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: Bondarchuk | Statement: [Natalya Bondarchuk, familyName, Bondarchuk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bondarchuk Context triple: [Natalya Bondarchuk, familyName, Bondarchuk]
-
A.
Bondarchuk
chosen
Bondarchuk is a notable Ukrainian-Russian surname most famously associated with Oscar-winning film director and actor Sergei Bondarchuk and his family of filmmakers and performers.
-
B.
Tartakovsky
Tartakovsky is a surname most prominently associated with Genndy Tartakovsky, the acclaimed animator and creator of series like Dexter’s Laboratory, Samurai Jack, and Primal.
-
C.
Aleksei Bondarchuk
Aleksei Bondarchuk is a Russian actor and film director known for his work in contemporary Russian cinema.
-
D.
Kurylenko
Kurylenko is a Ukrainian-origin surname most notably borne by actress and model Olga Kurylenko.
-
E.
Fyodor Bondarchuk
Fyodor Bondarchuk is a Russian film director, producer, and actor known for large-scale blockbusters such as "The 9th Company" and "Stalingrad."
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd81794819091b528600e322d7b |
completed | April 29, 2026, 3:36 a.m. |
Created at: April 17, 2026, 3:30 p.m.