Triple

T6432537
Position Surface form Disambiguated ID Type / Status
Subject Doctors' Plot E129811 entity
Predicate announcedBy P29 FINISHED
Object Pravda E8073 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: Pravda | Statement: [Doctors' Plot, announcedBy, Pravda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pravda
Context triple: [Doctors' Plot, announcedBy, Pravda]
  • A. Pravda chosen
    Pravda was the official newspaper of the Soviet Union’s Communist Party and a primary mouthpiece for state propaganda and ideology.
  • B. Pravda vítězí
    Pravda vítězí is the historic Czech national motto, meaning "Truth prevails," prominently associated with Czech statehood and democratic ideals.
  • C. Duma newspaper
    Duma newspaper is the official print media outlet associated with the Bulgarian Socialist Party, known for promoting its political views and covering national and political news in Bulgaria.
  • D. Pravdinsk
    Pravdinsk is a small town in Russia’s Kaliningrad Oblast, historically known as Friedland and noted as the site of a major 1807 Napoleonic battle.
  • E. Russkiy Vestnik
    Russkiy Vestnik was a prominent 19th-century Russian literary and political journal that published works by major authors such as Dostoevsky and Tolstoy.
  • 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_69c0084caac48190a7bc2ad8ba44536f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0693de6ac81909f3e330363a52102 completed March 22, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640ec681881909c75a55b33c09eb6 completed March 27, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:44 p.m.