Triple

T17696661
Position Surface form Disambiguated ID Type / Status
Subject Arabella E441188 entity
Predicate mainCharacter P1183 FINISHED
Object Zdenka 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: Zdenka | Statement: [Arabella, mainCharacter, Zdenka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zdenka
Context triple: [Arabella, mainCharacter, Zdenka]
  • A. Zdenka chosen
    Zdenka is a character in Richard Strauss’s opera "Arabella," known as Arabella’s younger sister who disguises herself as a boy.
  • B. Žofia
    Žofia is a feminine given name, commonly used in Slovak and other Slavic languages, equivalent to the name Sophia.
  • C. Božena
    Božena is a Czech feminine given name most famously borne by the 19th-century writer Božena Němcová, a key figure in Czech literature and national revival.
  • D. Libuše
    Libuše is a Czech opera by Bedřich Smetana, centered on the legendary princess Libuše who prophesies the glory of Prague and the Czech nation.
  • E. Dáša
    Dáša is a common Czech and Slovak feminine given name, typically used as a diminutive form of Dagmar.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47156a8f8819080cc730f4e9bc6ad completed April 19, 2026, 6:08 a.m.
Created at: April 10, 2026, 10:04 a.m.