Triple

T10446308
Position Surface form Disambiguated ID Type / Status
Subject Laurentius E246296 entity
Predicate hasVariant P455 FINISHED
Object Lavrenti E481377 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: Lavrenti | Statement: [Laurentius, hasVariant, Lavrenti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lavrenti
Context triple: [Laurentius, hasVariant, Lavrenti]
  • A. Lavrentiy chosen
    Lavrentiy was a Soviet politician and chief of Stalin’s secret police, notorious for his role in political repression and state security operations in the USSR.
  • B. Sergo Beria
    Sergo Beria was the son of Soviet secret police chief Lavrentiy Beria, known for his work as a Soviet military engineer and for later publishing memoirs about his father and the Stalin era.
  • C. Rykov
    Rykov is a Russian surname most notably associated with Alexei Rykov, a prominent early Soviet politician and premier.
  • D. Matakevich
    Matakevich is a surname most notably borne by American football linebacker and special teams standout Tyler Matakevich.
  • E. Anatoly Virgansky
    Anatoly Virgansky is best known as the husband of Irina Virganskaya, the daughter of former Soviet leader Leonid Brezhnev.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fdc0520c819098d2d53ee46a89ae completed April 7, 2026, 12:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69d933a2daf481908300a12d0f794e4c completed April 10, 2026, 5:30 p.m.
Created at: April 6, 2026, 12:16 p.m.