Triple

T10293691
Position Surface form Disambiguated ID Type / Status
Subject Koenigsegg Agera R E241427 entity
Predicate designer P184 FINISHED
Object Christian von Koenigsegg
Christian von Koenigsegg is a Swedish automotive entrepreneur and founder of the high-performance hypercar manufacturer Koenigsegg Automotive AB.
E855893 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: Christian von Koenigsegg | Statement: [Koenigsegg Agera R, designer, Christian von Koenigsegg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christian von Koenigsegg
Context triple: [Koenigsegg Agera R, designer, Christian von Koenigsegg]
  • A. Kay Fisker
    Kay Fisker was a prominent Danish architect known for his influential role in early 20th-century Nordic Classicism and for designing functional yet elegantly proportioned residential buildings.
  • B. Frank Kracht
    Frank Kracht is a German local politician who serves as the mayor of the Baltic Sea town of Sassnitz.
  • C. Claus Wellenreuther
    Claus Wellenreuther is a German entrepreneur best known as one of the co-founders of the enterprise software company SAP.
  • D. Adrian Johansson
    Adrian Johansson is the brother of American actress Scarlett Johansson.
  • E. Rainer Vossen
    Rainer Vossen is a linguist known for his extensive research on Khoe and other Khoisan languages of southern Africa.
  • 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: Christian von Koenigsegg
Triple: [Koenigsegg Agera R, designer, Christian von Koenigsegg]
Generated description
Christian von Koenigsegg is a Swedish automotive entrepreneur and founder of the high-performance hypercar manufacturer Koenigsegg Automotive AB.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Christian von Koenigsegg
Target entity description: Christian von Koenigsegg is a Swedish automotive entrepreneur and founder of the high-performance hypercar manufacturer Koenigsegg Automotive AB.
  • A. Kay Fisker
    Kay Fisker was a prominent Danish architect known for his influential role in early 20th-century Nordic Classicism and for designing functional yet elegantly proportioned residential buildings.
  • B. Frank Kracht
    Frank Kracht is a German local politician who serves as the mayor of the Baltic Sea town of Sassnitz.
  • C. Claus Wellenreuther
    Claus Wellenreuther is a German entrepreneur best known as one of the co-founders of the enterprise software company SAP.
  • D. Adrian Johansson
    Adrian Johansson is the brother of American actress Scarlett Johansson.
  • E. Rainer Vossen
    Rainer Vossen is a linguist known for his extensive research on Khoe and other Khoisan languages of southern Africa.
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2d46fb08190b7694290692e47dc completed April 7, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71d1c180481909ca9983e14cbb931 completed April 9, 2026, 3:29 a.m.
NEDg Description generation batch_69d73182d7548190ac15093aa7001db7 completed April 9, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_69d7336c06308190ac72154134a26842 completed April 9, 2026, 5:04 a.m.
Created at: April 6, 2026, 11:42 a.m.