Triple
T23087553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Ivanovich Ostermann-Tolstoy |
E575651
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Ostermann-Tolstoy |
—
|
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: Ostermann-Tolstoy | Statement: [Alexander Ivanovich Ostermann-Tolstoy, familyName, Ostermann-Tolstoy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ostermann-Tolstoy Context triple: [Alexander Ivanovich Ostermann-Tolstoy, familyName, Ostermann-Tolstoy]
-
A.
Ostermann-Tolstoy
chosen
Ostermann-Tolstoy is the noble Russian family name associated with Count Alexander Ivanovich Ostermann-Tolstoy, a prominent general of the Napoleonic Wars.
-
B.
Tolstaya
Tolstaya is a Russian noble family name most famously borne by Sophia Tolstaya, the wife and muse of writer Leo Tolstoy.
-
C.
Odoevsky
Odoevsky is the surname of a Russian princely family historically associated with the nobility of Muscovy and the Russian Empire.
-
D.
Rozhdestvensky
Rozhdestvensky is a Russian surname most notably associated with figures such as conductor Gennady Rozhdestvensky.
-
E.
Andrey Tolstoy
Andrey Tolstoy is an early patrilineal ancestor of the prominent Russian noble Tolstoy family.
- 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da652ac819085919ade6dd7bce4 |
completed | April 29, 2026, 4:48 a.m. |
Created at: April 17, 2026, 3:57 p.m.