Triple

T14065888
Position Surface form Disambiguated ID Type / Status
Subject Rebecca Randall E338469 entity
Predicate relative P37 FINISHED
Object John Randall
John Randall is a member of the Randall family, known primarily in relation to Rebecca Randall.
E1080081 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: John Randall | Statement: [Rebecca Randall, relative, John Randall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Randall
Context triple: [Rebecca Randall, relative, John Randall]
  • A. John Randall
    John Randall was a British physicist and biophysicist known for his leadership in molecular biology research at King's College London, where crucial work on the structure of DNA was carried out.
  • B. John Ernest Randall
    John Ernest Randall was a physicist and academic known for his contributions to nuclear physics and for being a prominent student of Ernest Marsden.
  • C. Freeman A. Davies
    Freeman A. Davies is a film editor best known for his work on the action-comedy movie "48 Hrs."
  • D. John Charles Woodward
    John Charles Woodward was an educator and philanthropist best known for establishing Woodward Academy, a prominent independent school in Georgia.
  • E. Robert Leighton
    Robert Leighton is a film editor known for his work on notable movies including the baseball romantic comedy "Bull Durham."
  • 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: John Randall
Triple: [Rebecca Randall, relative, John Randall]
Generated description
John Randall is a member of the Randall family, known primarily in relation to Rebecca Randall.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Randall
Target entity description: John Randall is a member of the Randall family, known primarily in relation to Rebecca Randall.
  • A. John Randall
    John Randall was a British physicist and biophysicist known for his leadership in molecular biology research at King's College London, where crucial work on the structure of DNA was carried out.
  • B. John Ernest Randall
    John Ernest Randall was a physicist and academic known for his contributions to nuclear physics and for being a prominent student of Ernest Marsden.
  • C. Freeman A. Davies
    Freeman A. Davies is a film editor best known for his work on the action-comedy movie "48 Hrs."
  • D. John Charles Woodward
    John Charles Woodward was an educator and philanthropist best known for establishing Woodward Academy, a prominent independent school in Georgia.
  • E. Robert Leighton
    Robert Leighton is a film editor known for his work on notable movies including the baseball romantic comedy "Bull Durham."
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de568b81f08190a571004261c0e8e4 completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd09db51c8190ab275e68b1aec120 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd340e25881908c2ff61a40da2e7a completed May 7, 2026, 6 p.m.
NED2 Entity disambiguation (via description) batch_69fcd3fe5f5081909291e8b9af77ee33 completed May 7, 2026, 6:03 p.m.
Created at: April 9, 2026, 10:21 p.m.