Triple

T18274188
Position Surface form Disambiguated ID Type / Status
Subject Zenit E437690 entity
Predicate upperStageOptions P37431 FINISHED
Object Fregat NE NERFINISHED

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: Fregat | Statement: [Zenit, upperStageOptions, Fregat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fregat
Context triple: [Zenit, upperStageOptions, Fregat]
  • A. Fregat chosen
    Fregat is a Russian expendable upper stage used to place payloads into a wide range of orbits on various launch vehicles such as Soyuz and Zenit.
  • B. Gepard-class frigate
    The Gepard-class frigate is a class of Russian multi-role warships designed for patrol, escort, and anti-submarine operations, used both by the Russian Navy and for export.
  • C. Koni-class frigate
    The Koni-class frigate is a Soviet-designed anti-submarine and patrol warship built primarily for export to allied navies during the Cold War.
  • D. Kamorta-class corvette
    The Kamorta-class corvette is a class of Indian-built anti-submarine warfare stealth corvettes designed for coastal and blue-water operations.
  • E. Type 31 frigate
    The Type 31 frigate is a new class of general-purpose warships being built for the Royal Navy, designed to provide flexible, cost-effective maritime security and escort capabilities.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50050d6688190b909a1c24e1dd3c9 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:34 a.m.