Triple

T20442124
Position Surface form Disambiguated ID Type / Status
Subject Academy of Fine Arts in Prague E501420 entity
Predicate hasNotableAlumni P51 FINISHED
Object Josef Čapek 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: Josef Čapek | Statement: [Academy of Fine Arts in Prague, hasNotableAlumni, Josef Čapek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Josef Čapek
Context triple: [Academy of Fine Arts in Prague, hasNotableAlumni, Josef Čapek]
  • A. Josef Čapek chosen
    Josef Čapek was a Czech painter, writer, and pioneering modernist artist, also known for coining the word "robot" that his brother Karel Čapek popularized.
  • B. Karel Čapek
    Karel Čapek was a Czech writer and playwright best known internationally for his science fiction works, including the play "R.U.R." which introduced the word "robot" to the world.
  • C. Karel Černý
    Karel Černý was a Czech production designer and art director renowned for his work on major films, including the period drama "Valmont."
  • D. Jaroslav Hašek
    Jaroslav Hašek was a Czech writer and satirist best known for his unfinished comic novel "The Good Soldier Švejk," a classic of anti-war literature.
  • E. Miroslav Hašek
    Miroslav Hašek is a Czech ice hockey player known for his career as a forward in European professional leagues.
  • 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_69e0b4ab3cfc8190ac9bf32e932316b1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e685f3b794819080745b135a305ba7 completed April 20, 2026, 8 p.m.
Created at: April 16, 2026, 11:32 a.m.