Triple
T16669219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sergei Kapitsa |
E405060
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Tatiana Kapitsa |
E405060
|
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: Tatiana Kapitsa | Statement: [Sergei Kapitsa, spouse, Tatiana Kapitsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tatiana Kapitsa Context triple: [Sergei Kapitsa, spouse, Tatiana Kapitsa]
-
A.
Tatiana Kapitsa
chosen
Tatiana Kapitsa is known as the wife of prominent Russian physicist and science popularizer Sergei Kapitsa.
-
B.
Maria Shubskaya
Maria Shubskaya is a Russian film producer and public figure known as the daughter of acclaimed actress and director Vera Glagoleva.
-
C.
Katia Kosterlitz
Katia Kosterlitz was the wife of German-born British pharmacologist Hermann Kosterlitz, known for his pioneering work on opioid receptors.
-
D.
Anna Khitrova
Anna Khitrova is a London midwife who becomes entangled with the Russian mafia while investigating a deceased teenager’s diary in the crime thriller film "Eastern Promises."
-
E.
Vera Kistiakowsky
Vera Kistiakowsky was an American experimental nuclear physicist and MIT professor known for her research in particle physics and her advocacy for women in science.
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37c9fa3d081909457b1bdea1d96e0 |
completed | April 18, 2026, 12:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091901fd88190a3c0e4b133121a02 |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:18 a.m.