Triple

T10235362
Position Surface form Disambiguated ID Type / Status
Subject Mendel University in Brno E243448 entity
Predicate hasRector P325 FINISHED
Object Jan Mareš
Jan Mareš is a Czech academic who serves as the rector of Mendel University in Brno.
E851529 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: Jan Mareš | Statement: [Mendel University in Brno, hasRector, Jan Mareš]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan Mareš
Context triple: [Mendel University in Brno, hasRector, Jan Mareš]
  • A. Jan Bulis
    Jan Bulis is a Czech former professional ice hockey forward who played in the NHL and KHL and represented the Czech national team internationally.
  • B. Viktor Pospíšil
    Viktor Pospíšil is a conductor and music director known for his leadership at the Staatsoper Stuttgart.
  • C. Jan Novák
    Jan Novák was a Czech composer known for his neoclassical style and film scores, including the music for the film "Atentát."
  • D. Karel Hermánek
    Karel Hermánek is a Czech actor known for his work in film, television, and theater, including a role in the 1993 war drama "Stalingrad."
  • E. Pavel Janák
    Pavel Janák was a prominent Czech architect and designer associated with Czech Cubism and later Functionalism, known for his innovative contributions to early 20th-century architecture and applied arts.
  • 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: Jan Mareš
Triple: [Mendel University in Brno, hasRector, Jan Mareš]
Generated description
Jan Mareš is a Czech academic who serves as the rector of Mendel University in Brno.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jan Mareš
Target entity description: Jan Mareš is a Czech academic who serves as the rector of Mendel University in Brno.
  • A. Jan Bulis
    Jan Bulis is a Czech former professional ice hockey forward who played in the NHL and KHL and represented the Czech national team internationally.
  • B. Viktor Pospíšil
    Viktor Pospíšil is a conductor and music director known for his leadership at the Staatsoper Stuttgart.
  • C. Jan Novák
    Jan Novák was a Czech composer known for his neoclassical style and film scores, including the music for the film "Atentát."
  • D. Karel Hermánek
    Karel Hermánek is a Czech actor known for his work in film, television, and theater, including a role in the 1993 war drama "Stalingrad."
  • E. Pavel Janák
    Pavel Janák was a prominent Czech architect and designer associated with Czech Cubism and later Functionalism, known for his innovative contributions to early 20th-century architecture and applied arts.
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d20de15c8190a81f3e9803fdfcd1 completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f757b514819087f5d5f659c50c66 completed April 9, 2026, 12:48 a.m.
NEDg Description generation batch_69d6fa2ea97081908395048218c0592b completed April 9, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_69d6fcb5dc4c8190944a423a9d16a4b8 completed April 9, 2026, 1:11 a.m.
Created at: April 6, 2026, 11:21 a.m.