Triple

T17153685
Position Surface form Disambiguated ID Type / Status
Subject Karel Kramář E416286 entity
Predicate familyName P18 FINISHED
Object Kramář
Kramář is a Czech surname most notably borne by Karel Kramář, the first Prime Minister of Czechoslovakia and a prominent early 20th-century politician.
 E1252859 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: Kramář | Statement: [Karel Kramář, familyName, Kramář]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kramář
Context triple: [Karel Kramář, familyName, Kramář]
  • A. Krejčíř
    Krejčíř is a Czech surname most notably associated with Radovan Krejčíř, a convicted criminal and fugitive involved in high-profile fraud and organized crime cases.
  • B. Havlíček
    Havlíček is a Czech surname most famously associated with basketball Hall of Famer John Havlicek and several notable Czech cultural and public figures.
  • C. Olejkár
    Olejkár is a Slovak literary work by Jozef Miloslav Hurban, reflecting 19th-century Slovak national and cultural themes.
  • D. Zdeněk
    Zdeněk is a Czech given name commonly used for males, equivalent to the English name Sidney or Dennis in some contexts.
  • E. Lumír Hanuš
    Lumír Hanuš is a Czech analytical chemist and cannabis researcher best known for co-discovering the endocannabinoid anandamide.
  • 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: Kramář
Triple: [Karel Kramář, familyName, Kramář]
Generated description
Kramář is a Czech surname most notably borne by Karel Kramář, the first Prime Minister of Czechoslovakia and a prominent early 20th-century politician.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kramář
Target entity description: Kramář is a Czech surname most notably borne by Karel Kramář, the first Prime Minister of Czechoslovakia and a prominent early 20th-century politician.
  • A. Krejčíř
    Krejčíř is a Czech surname most notably associated with Radovan Krejčíř, a convicted criminal and fugitive involved in high-profile fraud and organized crime cases.
  • B. Havlíček
    Havlíček is a Czech surname most famously associated with basketball Hall of Famer John Havlicek and several notable Czech cultural and public figures.
  • C. Olejkár
    Olejkár is a Slovak literary work by Jozef Miloslav Hurban, reflecting 19th-century Slovak national and cultural themes.
  • D. Zdeněk
    Zdeněk is a Czech given name commonly used for males, equivalent to the English name Sidney or Dennis in some contexts.
  • E. Lumír Hanuš
    Lumír Hanuš is a Czech analytical chemist and cannabis researcher best known for co-discovering the endocannabinoid anandamide.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f4092c40819096359ff90af16c3e completed April 18, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01415d19288190beb3c94da2ce8c0e completed May 11, 2026, 2:39 a.m.
NEDg Description generation batch_6a01422c0f088190b162c7086bc93585 completed May 11, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_6a0142f274ec819081eb15a3ea0e1b13 completed May 11, 2026, 2:46 a.m.
Created at: April 10, 2026, 5:37 a.m.