Triple
T2859887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vasily Stalin |
E63293
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Lydia Ivanova |
E63293
|
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: Lydia Ivanova | Statement: [Vasily Stalin, spouse, Lydia Ivanova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lydia Ivanova Context triple: [Vasily Stalin, spouse, Lydia Ivanova]
-
A.
Lydia Ivanova
chosen
Lydia Ivanova was the wife of Vasily Stalin, son of Soviet leader Joseph Stalin, and is primarily known for her connection to the Stalin family.
-
B.
Tatyana
Tatyana is a feminine given name of Slavic origin, particularly common in Russian-speaking countries.
-
C.
Lyudmila
Lyudmila is a Russian linguist and the former First Lady of Russia, known for being the ex-wife of President Vladimir Putin.
-
D.
Celia Lovsky
Celia Lovsky was an Austrian-American character actress known for her distinctive roles in mid-20th-century film and television, including a memorable appearance as T’Pau in the original Star Trek series.
-
E.
Xenia Shestova
Xenia Shestova was a Russian noblewoman and influential matriarch of the early Romanov dynasty, best known as the mother of Tsar Mikhail I of Russia.
- 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf8aec3c8190a4168d8c916b5268 |
completed | March 7, 2026, 8:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b03147229c81909e2f47f1ec40633d |
completed | March 10, 2026, 2:57 p.m. |
Created at: March 6, 2026, 10:02 p.m.