Triple
T20998073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalia Petrovna of Russia |
E517202
|
entity |
| Predicate | patronymicName |
P7966
|
FINISHED |
| Object | Petrovna |
—
|
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: Petrovna | Statement: [Natalia Petrovna of Russia, patronymicName, Petrovna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petrovna Context triple: [Natalia Petrovna of Russia, patronymicName, Petrovna]
-
A.
Petrovna
chosen
Petrovna is a common Russian patronymic derived from the male given name Pyotr, typically meaning "daughter of Pyotr."
-
B.
Pavlovna
Pavlovna is a Russian patronymic indicating "daughter of Pavel," commonly used as the middle name of women in Russian naming tradition.
-
C.
Mikhailovna
Mikhailovna is a Russian patronymic indicating descent from a father named Mikhail, commonly used as the middle name in female full names.
-
D.
Nikolaevna
Nikolaevna is a Russian patronymic indicating "daughter of Nikolai," famously borne by Grand Duchess Anastasia Nikolaevna of Russia.
-
E.
Princess Shcherbatskaya
Princess Shcherbatskaya is a noblewoman in Leo Tolstoy's novel "Anna Karenina," best known as the mother of Kitty (Ekaterina Alexandrovna Shcherbatskaya) and Dolly.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc22ca6081908bf054ddcfea9e19 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:51 p.m.