Triple

T3193169
Position Surface form Disambiguated ID Type / Status
Subject Roxana E66871 entity
Predicate hasVariant P455 FINISHED
Object Roksana
Roksana is a feminine given name, commonly used in various Slavic and Persian-influenced cultures, that is a variant of the name Roxana.
 E339306 NE FINISHED

How this triple was built (4 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: Roksana | Statement: [Roxana, hasVariant, Roksana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Roksana
Context triple: [Roxana, hasVariant, Roksana]
  • A. Aleksandra
    Aleksandra is a feminine given name of Slavic origin, commonly used in various Eastern and Central European countries.
  • B. Raisa
    Raisa Gorbacheva was the influential and highly visible wife of Soviet leader Mikhail Gorbachev, known for her intellectual background, public role, and charitable work.
  • C. Sylwia
    Sylwia is a feminine given name, primarily used in Poland, that is a cognate of the name Sylvia.
  • D. Klaudija
    Klaudija is a feminine given name, commonly used in Slavic countries, that corresponds to the name Claudia.
  • E. Romina
    Romina is an Italian-American actress and singer best known as half of the pop duo Al Bano & Romina Power.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Roksana
Triple: [Roxana, hasVariant, Roksana]
Generated description
Roksana is a feminine given name, commonly used in various Slavic and Persian-influenced cultures, that is a variant of the name Roxana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Roksana
Target entity description: Roksana is a feminine given name, commonly used in various Slavic and Persian-influenced cultures, that is a variant of the name Roxana.
  • A. Aleksandra
    Aleksandra is a feminine given name of Slavic origin, commonly used in various Eastern and Central European countries.
  • B. Raisa
    Raisa Gorbacheva was the influential and highly visible wife of Soviet leader Mikhail Gorbachev, known for her intellectual background, public role, and charitable work.
  • C. Sylwia
    Sylwia is a feminine given name, primarily used in Poland, that is a cognate of the name Sylvia.
  • D. Klaudija
    Klaudija is a feminine given name, commonly used in Slavic countries, that corresponds to the name Claudia.
  • E. Romina
    Romina is an Italian-American actress and singer best known as half of the pop duo Al Bano & Romina Power.
  • F. None of above. chosen

Provenance (5 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada713bf0c81908f3143f45f63a5ad completed March 8, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b276fbb7c481909097f5af619e45f4 completed March 12, 2026, 8:19 a.m.
NEDg Description generation batch_69b27844c6708190ac61f00a74a2ef27 completed March 12, 2026, 8:24 a.m.
NED2 Entity disambiguation (via description) batch_69b27911ff1481908a36f279a871c510 completed March 12, 2026, 8:28 a.m.
Created at: March 8, 2026, 3:07 p.m.