Triple

T13122430
Position Surface form Disambiguated ID Type / Status
Subject Roman Šebrle E311757 entity
Predicate name P16 FINISHED
Object Roman Šebrle E311757 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: Roman Šebrle | Statement: [Roman Šebrle, name, Roman Šebrle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman Šebrle
Context triple: [Roman Šebrle, name, Roman Šebrle]
  • A. Roman Šebrle chosen
    Roman Šebrle is a Czech former decathlete who became the first man to surpass 9,000 points in the decathlon and was one of the event’s dominant figures in the early 2000s.
  • B. Emil Zátopek
    Emil Zátopek was a legendary Czech long-distance runner renowned for his multiple Olympic gold medals and pioneering, brutally intense training methods.
  • C. Milko Skofic
    Milko Skofic was a Yugoslav-born physician and film producer best known as the former husband and manager of Italian actress Gina Lollobrigida.
  • D. Andrej Sustr
    Andrej Šustr is a Czech professional ice hockey defenseman who has played in the NHL, most notably for the Tampa Bay Lightning.
  • E. Jaromír Štětina
    Jaromír Štětina is a Czech journalist, war correspondent, and politician known for his reporting from conflict zones and his later service as a senator and Member of the European Parliament.
  • 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_69d806a9fe888190b081e2d9ea665d6c completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9819840b881909b76022b4c4dcaed completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e289462c8190b1625a26f019d744 completed May 3, 2026, 5:52 a.m.
Created at: April 9, 2026, 9:07 p.m.