Triple

T571553
Position Surface form Disambiguated ID Type / Status
Subject Charles E13673 entity
Predicate hasVariant P455 FINISHED
Object Károly
Károly is the Hungarian form of the given name Charles, commonly used as a male first name in Hungary.
E79472 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: Károly | Statement: [Charles, hasVariant, Károly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Károly
Context triple: [Charles, hasVariant, Károly]
  • A. Gábor
    Gábor is a Hungarian masculine given name, commonly used as the local form of Gabriel.
  • B. Gróf András István
    Gróf András István, better known as Andrew S. Grove, was a Hungarian-American engineer, businessman, and co-founder and longtime CEO of Intel who played a pivotal role in the rise of the semiconductor industry and Silicon Valley.
  • C. Stephen I of Hungary
    Stephen I of Hungary was the first King of Hungary, who converted the country to Christianity and established it as a Christian kingdom in the early 11th century.
  • D. Pál
    Pál is a Hungarian given name, equivalent to the English name Paul.
  • E. János Gálicz
    János Gálicz was a Hungarian-born military officer who served as a commander in the International Brigades during the Spanish Civil War.
  • 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: Károly
Triple: [Charles, hasVariant, Károly]
Generated description
Károly is the Hungarian form of the given name Charles, commonly used as a male first name in Hungary.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Károly
Target entity description: Károly is the Hungarian form of the given name Charles, commonly used as a male first name in Hungary.
  • A. Gábor
    Gábor is a Hungarian masculine given name, commonly used as the local form of Gabriel.
  • B. Gróf András István
    Gróf András István, better known as Andrew S. Grove, was a Hungarian-American engineer, businessman, and co-founder and longtime CEO of Intel who played a pivotal role in the rise of the semiconductor industry and Silicon Valley.
  • C. Stephen I of Hungary
    Stephen I of Hungary was the first King of Hungary, who converted the country to Christianity and established it as a Christian kingdom in the early 11th century.
  • D. Pál
    Pál is a Hungarian given name, equivalent to the English name Paul.
  • E. János Gálicz
    János Gálicz was a Hungarian-born military officer who served as a commander in the International Brigades during the Spanish Civil War.
  • 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_69a4933fa4d88190a7949cc83c08c5c1 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49b483ac08190b3be152a7cf42011 completed March 1, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69a56eeb783c819096d6557d31608ce4 completed March 2, 2026, 11:05 a.m.
NEDg Description generation batch_69a56f749cb48190b0976b157309dc84 completed March 2, 2026, 11:07 a.m.
NED2 Entity disambiguation (via description) batch_69a56fedabcc8190a6dd0a268350ca5d completed March 2, 2026, 11:09 a.m.
Created at: March 1, 2026, 7:33 p.m.