Triple
T19934443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oksana Markarova |
E479137
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Markarova |
E479137
|
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: Markarova | Statement: [Oksana Markarova, familyName, Markarova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Markarova Context triple: [Oksana Markarova, familyName, Markarova]
-
A.
Markarova
chosen
Markarova is a Ukrainian surname most notably borne by Oksana Markarova, Ukraine’s former finance minister and current ambassador to the United States.
-
B.
Arapova
Arapova is a Russian-language surname historically borne by various individuals of Slavic origin.
-
C.
Karsavina
Karsavina is the surname of Tamara Karsavina, a renowned Russian prima ballerina of the early 20th century.
-
D.
Komarova
Komarova is the feminine form of the Russian surname Komarov, commonly borne by women in Russian-speaking countries.
-
E.
Marfa Apraksina
Marfa Apraksina was a Russian noblewoman from the influential Apraksin family who became the wife of Tsarevich Fyodor Alexeyevich and mother of Tsarevich Ilya Fyodorovich in the late 17th century.
- 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a161a6c819084165ea528ec2f64 |
completed | April 20, 2026, 4:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07f6e830c88190be3af821423d89ee |
completed | May 16, 2026, 4:47 a.m. |
Created at: April 10, 2026, 1:53 p.m.