Triple

T21608771
Position Surface form Disambiguated ID Type / Status
Subject Olga Rozanova E533244 entity
Predicate familyName P18 FINISHED
Object Rozanova
Rozanova is a Russian surname most notably associated with Olga Rozanova, an influential early 20th-century avant-garde artist.
E1493255 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: Rozanova | Statement: [Olga Rozanova, familyName, Rozanova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rozanova
Context triple: [Olga Rozanova, familyName, Rozanova]
  • A. Ružička
    Ružička is a Croatian-origin surname most famously borne by Nobel Prize–winning chemist Leopold Ružička.
  • B. Rózsa
    Rózsa is the Hungarian given name of Rosika Schwimmer, a prominent early 20th-century feminist, pacifist, and suffragist activist.
  • C. Nadiža
    Nadiža is a river in the western Balkans, known for its clear waters and scenic course through the mountainous border region between Slovenia and Italy.
  • D. Nosková
    Nosková is a Czech surname, typically the feminine form of the surname Nosek.
  • E. Ruzena
    Ruzena is a central female character in Milan Kundera’s novel "Farewell Waltz," whose romantic entanglements and emotional turmoil drive much of the story’s tension.
  • 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: Rozanova
Triple: [Olga Rozanova, familyName, Rozanova]
Generated description
Rozanova is a Russian surname most notably associated with Olga Rozanova, an influential early 20th-century avant-garde artist.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rozanova
Target entity description: Rozanova is a Russian surname most notably associated with Olga Rozanova, an influential early 20th-century avant-garde artist.
  • A. Ružička
    Ružička is a Croatian-origin surname most famously borne by Nobel Prize–winning chemist Leopold Ružička.
  • B. Rózsa
    Rózsa is the Hungarian given name of Rosika Schwimmer, a prominent early 20th-century feminist, pacifist, and suffragist activist.
  • C. Nadiža
    Nadiža is a river in the western Balkans, known for its clear waters and scenic course through the mountainous border region between Slovenia and Italy.
  • D. Nosková
    Nosková is a Czech surname, typically the feminine form of the surname Nosek.
  • E. Ruzena
    Ruzena is a central female character in Milan Kundera’s novel "Farewell Waltz," whose romantic entanglements and emotional turmoil drive much of the story’s tension.
  • 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_69e0c46411108190bba0d4176dffc9f3 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef17e7005c81908cfa86358b8dbef1 completed April 27, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09fd3b13c881909eb8eee8ad8242be completed May 17, 2026, 5:39 p.m.
NEDg Description generation batch_6a09fe7380c881909d17d5ba64f0b19f completed May 17, 2026, 5:44 p.m.
NED2 Entity disambiguation (via description) batch_6a09fef4abe48190b6eac6d14aadd110 completed May 17, 2026, 5:46 p.m.
Created at: April 16, 2026, 6:33 p.m.