Triple

T7053978
Position Surface form Disambiguated ID Type / Status
Subject Mihály Károlyi E164038 entity
Predicate familyName P18 FINISHED
Object Károlyi
Károlyi is a Hungarian noble family name most prominently associated with Mihály Károlyi, a key political figure and leader during Hungary’s transition after World War I.
 E643813 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: Károlyi | Statement: [Mihály Károlyi, familyName, Károlyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Károlyi
Context triple: [Mihály Károlyi, familyName, Károlyi]
  • A. Miklós
    Miklós is a Hungarian masculine given name, equivalent to Nicholas in English.
  • B. Kálmán
    Kálmán is a Hungarian surname most notably associated with Rudolf E. Kálmán, the pioneering engineer and mathematician behind the Kalman filter.
  • C. Károly
    Károly is the Hungarian form of the given name Charles, commonly used as a male first name in Hungary.
  • D. Ernő
    Ernő is a Hungarian-born British modernist architect best known for his influential and often controversial Brutalist buildings in London.
  • E. István
    István is the Hungarian given name of Stephen I of Hungary, the first Christian king and founder of the medieval Hungarian state.
  • 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: Károlyi
Triple: [Mihály Károlyi, familyName, Károlyi]
Generated description
Károlyi is a Hungarian noble family name most prominently associated with Mihály Károlyi, a key political figure and leader during Hungary’s transition after World War I.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Károlyi
Target entity description: Károlyi is a Hungarian noble family name most prominently associated with Mihály Károlyi, a key political figure and leader during Hungary’s transition after World War I.
  • A. Miklós
    Miklós is a Hungarian masculine given name, equivalent to Nicholas in English.
  • B. Kálmán
    Kálmán is a Hungarian surname most notably associated with Rudolf E. Kálmán, the pioneering engineer and mathematician behind the Kalman filter.
  • C. Károly
    Károly is the Hungarian form of the given name Charles, commonly used as a male first name in Hungary.
  • D. Ernő
    Ernő is a Hungarian-born British modernist architect best known for his influential and often controversial Brutalist buildings in London.
  • E. István
    István is the Hungarian given name of Stephen I of Hungary, the first Christian king and founder of the medieval Hungarian state.
  • 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_69c68861678881909961ddf4d779f750 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e265ea348190a9bd3807c0d605d8 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a316374c81908deeb60b8f58a3c8 completed March 28, 2026, 9:44 a.m.
NEDg Description generation batch_69c7a41986308190ac540663ddfd6802 completed March 28, 2026, 9:49 a.m.
NED2 Entity disambiguation (via description) batch_69c7a4be1cbc8190a7e4eb91d604f994 completed March 28, 2026, 9:51 a.m.
Created at: March 27, 2026, 2:37 p.m.