Triple

T12338851
Position Surface form Disambiguated ID Type / Status
Subject Maria Spiridonova E294165 entity
Predicate placeOfDeath P21 FINISHED
Object Oryol E261239 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: Oryol | Statement: [Maria Spiridonova, placeOfDeath, Oryol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oryol
Context triple: [Maria Spiridonova, placeOfDeath, Oryol]
  • A. Oryol
    Oryol was a notable warship of the Imperial Russian Navy, recognized for its role in Russia’s early modern naval history.
  • B. Tambov
    Tambov is a city in western Russia known as an administrative, cultural, and industrial center of the Tambov Oblast.
  • C. Belgorod
    Belgorod is a city in western Russia near the Ukrainian border, historically significant as a strategic site of major World War II battles and offensives.
  • D. Ryazan
    Ryazan is a historic city in western Russia known for its medieval kremlin, role as a regional cultural and economic center, and legacy as one of the country’s oldest urban settlements.
  • E. Oryol Governorate chosen
    Oryol Governorate was an administrative division of the Russian Empire and early Russian SFSR centered on the city of Oryol, historically located in western Russia.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f678698819091462b44ff3435f6 completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79418e26c819088f3aa608d9d65d6 completed May 3, 2026, 6:29 p.m.
Created at: April 8, 2026, 9:53 p.m.