Triple
T23069408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyotr Andreyevich Tolstoy |
E575149
|
entity |
| Predicate | patronymicName |
P7966
|
FINISHED |
| Object | Andreyevich |
—
|
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: Andreyevich | Statement: [Pyotr Andreyevich Tolstoy, patronymicName, Andreyevich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andreyevich Context triple: [Pyotr Andreyevich Tolstoy, patronymicName, Andreyevich]
-
A.
Andreievich
chosen
Andreievich is a Russian patronymic indicating that a man is the son of someone named Andrei.
-
B.
Arkadyevich
Arkadyevich is the patronymic of Stepan Arkadyevich Oblonsky, a central socialite and bureaucratic character in Leo Tolstoy’s novel "Anna Karenina."
-
C.
Anatolyevich
Anatolyevich is a Russian patronymic given name indicating that a person is the son of someone named Anatoly.
-
D.
Alexandrovich
Alexandrovich is the Russian patronymic indicating "son of Alexander," famously used in the full name of Tsar Nicholas II of Russia.
-
E.
Andrey Andreevich Andriyashev
Andrey Andreevich Andriyashev was a prominent Russian ichthyologist known for his extensive research on deep-sea and polar fishes.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a676c08190863c034663406018 |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.