Triple

T21093839
Position Surface form Disambiguated ID Type / Status
Subject Karpf E519707 entity
Predicate hasNotableBearer P458 FINISHED
Object Michael Karpf
Michael Karpf is a British physician and academic leader best known for his roles in hospital administration and medical education.
E1505312 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: Michael Karpf | Statement: [Karpf, hasNotableBearer, Michael Karpf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Karpf
Context triple: [Karpf, hasNotableBearer, Michael Karpf]
  • A. Michael Vavitch
    Michael Vavitch was a silent-era film actor known for his role in the 1924 drama "The Red Lily."
  • B. Michael E. Bakich
    Michael E. Bakich is an American astronomy writer, editor, and popularizer of observational astronomy, long associated with Astronomy magazine.
  • C. Michael Wittenberg
    Michael Wittenberg was an investment adviser best known as the late husband of Broadway star Bernadette Peters.
  • D. Alan Schaefer
    Alan Schaefer is the main special-forces commando protagonist, nicknamed "Dutch," portrayed by Arnold Schwarzenegger in the 1987 science fiction action film Predator.
  • E. John Eisendrath
    John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
  • 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: Michael Karpf
Triple: [Karpf, hasNotableBearer, Michael Karpf]
Generated description
Michael Karpf is a British physician and academic leader best known for his roles in hospital administration and medical education.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Karpf
Target entity description: Michael Karpf is a British physician and academic leader best known for his roles in hospital administration and medical education.
  • A. Michael Vavitch
    Michael Vavitch was a silent-era film actor known for his role in the 1924 drama "The Red Lily."
  • B. Michael E. Bakich
    Michael E. Bakich is an American astronomy writer, editor, and popularizer of observational astronomy, long associated with Astronomy magazine.
  • C. Michael Wittenberg
    Michael Wittenberg was an investment adviser best known as the late husband of Broadway star Bernadette Peters.
  • D. Alan Schaefer
    Alan Schaefer is the main special-forces commando protagonist, nicknamed "Dutch," portrayed by Arnold Schwarzenegger in the 1987 science fiction action film Predator.
  • E. John Eisendrath
    John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e709517a18819081ede1d38e2c4391 completed April 21, 2026, 5:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a4bb108e08190ac6036fc6259cd8b completed May 17, 2026, 11:13 p.m.
NEDg Description generation batch_6a0a4ccdd0a881908d32425b7cbb30c4 completed May 17, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_6a0a4de7d07c8190a0ccb1c229e7fc5d completed May 17, 2026, 11:23 p.m.
Created at: April 16, 2026, 2:51 p.m.