Triple

T1478667
Position Surface form Disambiguated ID Type / Status
Subject Peter Kapitza E30900 entity
Predicate familyName P18 FINISHED
Object Kapitza E85626 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: Kapitza | Statement: [Peter Kapitza, familyName, Kapitza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kapitza
Context triple: [Peter Kapitza, familyName, Kapitza]
  • A. Peter Kapitza
    Peter Kapitza was a Soviet physicist and Nobel laureate renowned for his pioneering work in low-temperature physics and the study of liquid helium.
  • B. Kistiakowsky
    Kistiakowsky is a surname most notably associated with George Kistiakowsky, a Ukrainian-American physical chemist who contributed to the Manhattan Project and later served as a science advisor to U.S. President Dwight D. Eisenhower.
  • C. Sergei Kapitsa chosen
    Sergei Kapitsa was a Russian physicist and demographer best known for popularizing science on Soviet television and for his work on population dynamics.
  • D. Lindemann
    Lindemann is a German surname most notably associated with Ferdinand von Lindemann, the mathematician who proved that π is a transcendental number.
  • E. Rubbia
    Rubbia is the surname of Carlo Rubbia, an Italian physicist and Nobel laureate known for his contributions to particle physics.
  • 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_69a498fe55a88190ab7f9e40ace88e49 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c6739d2481909ea8d8e075f62cf3 completed March 1, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1ca21f288190b5f6f9a5895cdcf0 completed March 8, 2026, 6:52 a.m.
Created at: March 1, 2026, 8:11 p.m.