Triple

T12558139
Position Surface form Disambiguated ID Type / Status
Subject Joe Calzaghe E295270 entity
Predicate notableVictoryOver P34090 FINISHED
Object Mikkel Kessler
Mikkel Kessler is a Danish former professional boxer and multiple-time super middleweight world champion known for his technical skill and powerful jab.
E990878 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: Mikkel Kessler | Statement: [Joe Calzaghe, notableVictoryOver, Mikkel Kessler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mikkel Kessler
Context triple: [Joe Calzaghe, notableVictoryOver, Mikkel Kessler]
  • A. Mikkel Bondesen
    Mikkel Bondesen is a television producer known for his executive production work on series such as "The Comedians."
  • B. Mikael Jorgensen
    Mikael Jorgensen is an American musician and keyboardist best known for his long-time role in the alternative rock band Wilco.
  • C. Mikkel Svane
    Mikkel Svane is a Danish entrepreneur best known as the co-founder and longtime CEO of the customer service software company Zendesk.
  • D. Mikkel Eriksen
    Mikkel Eriksen is a Norwegian record producer and songwriter best known as one half of the production duo Stargate, which has crafted numerous global pop and R&B hits.
  • E. Peter Høj
    Peter Høj is an Australian academic and university leader who has served as vice-chancellor at several major universities, including the University of Adelaide.
  • 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: Mikkel Kessler
Triple: [Joe Calzaghe, notableVictoryOver, Mikkel Kessler]
Generated description
Mikkel Kessler is a Danish former professional boxer and multiple-time super middleweight world champion known for his technical skill and powerful jab.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mikkel Kessler
Target entity description: Mikkel Kessler is a Danish former professional boxer and multiple-time super middleweight world champion known for his technical skill and powerful jab.
  • A. Mikkel Bondesen
    Mikkel Bondesen is a television producer known for his executive production work on series such as "The Comedians."
  • B. Mikael Jorgensen
    Mikael Jorgensen is an American musician and keyboardist best known for his long-time role in the alternative rock band Wilco.
  • C. Mikkel Svane
    Mikkel Svane is a Danish entrepreneur best known as the co-founder and longtime CEO of the customer service software company Zendesk.
  • D. Mikkel Eriksen
    Mikkel Eriksen is a Norwegian record producer and songwriter best known as one half of the production duo Stargate, which has crafted numerous global pop and R&B hits.
  • E. Peter Høj
    Peter Høj is an Australian academic and university leader who has served as vice-chancellor at several major universities, including the University of Adelaide.
  • 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95491d9688190a6b88a939124233e completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f655895c9c819082f41e79906567c6 completed May 2, 2026, 7:50 p.m.
NEDg Description generation batch_69f6599e89708190bc1d38e9702d7626 completed May 2, 2026, 8:07 p.m.
NED2 Entity disambiguation (via description) batch_69f65a414118819095049600f1ad6d63 completed May 2, 2026, 8:10 p.m.
Created at: April 8, 2026, 11:48 p.m.