Triple

T16241105
Position Surface form Disambiguated ID Type / Status
Subject Petr Pavel E394246 entity
Predicate spouse P13 FINISHED
Object Eva Pavlová
Eva Pavlová is a Czech public figure and former military officer best known as the wife of Czech President Petr Pavel and the country's First Lady.
 E1202300 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: Eva Pavlová | Statement: [Petr Pavel, spouse, Eva Pavlová]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Eva Pavlová
Context triple: [Petr Pavel, spouse, Eva Pavlová]
  • A. Eva Němcová
    Eva Němcová is a former Czech professional basketball player best known as a standout forward in the WNBA during the late 1990s and early 2000s.
  • B. Eva Herzigová
    Eva Herzigová is a Czech supermodel and actress who rose to international fame in the 1990s, particularly as a prominent face of the Wonderbra campaign.
  • C. Eva Dzurindová
    Eva Dzurindová is known as the wife of Slovak politician and former prime minister Mikuláš Dzurinda.
  • D. Eva Ondříčková
    Eva Ondříčková is known as the wife of acclaimed Czech cinematographer Miroslav Ondříček.
  • E. Dagmar Havlová
    Dagmar Havlová is a Czech actress and former First Lady of the Czech Republic, known for her film and theater work as well as her marriage to President Václav Havel.
  • 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: Eva Pavlová
Triple: [Petr Pavel, spouse, Eva Pavlová]
Generated description
Eva Pavlová is a Czech public figure and former military officer best known as the wife of Czech President Petr Pavel and the country's First Lady.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Eva Pavlová
Target entity description: Eva Pavlová is a Czech public figure and former military officer best known as the wife of Czech President Petr Pavel and the country's First Lady.
  • A. Eva Němcová
    Eva Němcová is a former Czech professional basketball player best known as a standout forward in the WNBA during the late 1990s and early 2000s.
  • B. Eva Herzigová
    Eva Herzigová is a Czech supermodel and actress who rose to international fame in the 1990s, particularly as a prominent face of the Wonderbra campaign.
  • C. Eva Dzurindová
    Eva Dzurindová is known as the wife of Slovak politician and former prime minister Mikuláš Dzurinda.
  • D. Eva Ondříčková
    Eva Ondříčková is known as the wife of acclaimed Czech cinematographer Miroslav Ondříček.
  • E. Dagmar Havlová
    Dagmar Havlová is a Czech actress and former First Lady of the Czech Republic, known for her film and theater work as well as her marriage to President Václav Havel.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2455e1ce08190b97e2ab3e8c6d535 completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000edd1ed08190aa0211c3b17a918e completed May 10, 2026, 4:51 a.m.
NEDg Description generation batch_6a00108fdda88190bf510d04f4cc73f1 completed May 10, 2026, 4:58 a.m.
NED2 Entity disambiguation (via description) batch_6a0011559b748190ad406263889514a4 completed May 10, 2026, 5:02 a.m.
Created at: April 10, 2026, 5:04 a.m.