Triple

T17135612
Position Surface form Disambiguated ID Type / Status
Subject Lány E415827 entity
Predicate significantPerson P643 FINISHED
Object Miloš Zeman
Miloš Zeman is a Czech politician who served as the President of the Czech Republic from 2013 to 2023 and previously as the country’s Prime Minister.
E1254034 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: Miloš Zeman | Statement: [Lány, significantPerson, Miloš Zeman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miloš Zeman
Context triple: [Lány, significantPerson, Miloš Zeman]
  • A. Radek Duda
    Radek Duda is a Czech professional ice hockey player known for his long career as a forward in the Czech Extraliga and various European leagues.
  • B. Pavel Baudiš
    Pavel Baudiš is a Czech software engineer and entrepreneur best known as a co-founder of the cybersecurity company Avast.
  • C. Petr Pavel
    Petr Pavel is a Czech politician and retired army general who serves as the President of the Czech Republic.
  • D. Václav Klaus
    Václav Klaus is a Czech economist and conservative politician who served as both Prime Minister and later President of the Czech Republic.
  • E. Mikuláš Dzurinda
    Mikuláš Dzurinda is a Slovak politician who served as Prime Minister of Slovakia from 1998 to 2006 and played a key role in the country’s integration into NATO and the European Union.
  • 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: Miloš Zeman
Triple: [Lány, significantPerson, Miloš Zeman]
Generated description
Miloš Zeman is a Czech politician who served as the President of the Czech Republic from 2013 to 2023 and previously as the country’s Prime Minister.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Miloš Zeman
Target entity description: Miloš Zeman is a Czech politician who served as the President of the Czech Republic from 2013 to 2023 and previously as the country’s Prime Minister.
  • A. Radek Duda
    Radek Duda is a Czech professional ice hockey player known for his long career as a forward in the Czech Extraliga and various European leagues.
  • B. Pavel Baudiš
    Pavel Baudiš is a Czech software engineer and entrepreneur best known as a co-founder of the cybersecurity company Avast.
  • C. Petr Pavel
    Petr Pavel is a Czech politician and retired army general who serves as the President of the Czech Republic.
  • D. Václav Klaus
    Václav Klaus is a Czech economist and conservative politician who served as both Prime Minister and later President of the Czech Republic.
  • E. Mikuláš Dzurinda
    Mikuláš Dzurinda is a Slovak politician who served as Prime Minister of Slovakia from 1998 to 2006 and played a key role in the country’s integration into NATO and the European Union.
  • 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_69d886d15af4819092f92f8a129763e6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f02dca8881908efd73741397a207 completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01482cd918819082d18b3cb76394cb completed May 11, 2026, 3:08 a.m.
NEDg Description generation batch_6a01498352648190a28be189af2263ea completed May 11, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_6a014a3e36588190b15fa0fe958e2d9e completed May 11, 2026, 3:17 a.m.
Created at: April 10, 2026, 5:36 a.m.