Triple

T22321825
Position Surface form Disambiguated ID Type / Status
Subject Cokie Roberts E551804 entity
Predicate hasChild P369 FINISHED
Object Lee Roberts
Lee Roberts is a child of the late American journalist and political commentator Cokie Roberts.
E1545109 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: Lee Roberts | Statement: [Cokie Roberts, hasChild, Lee Roberts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lee Roberts
Context triple: [Cokie Roberts, hasChild, Lee Roberts]
  • A. Sam Rolfe
    Sam Rolfe was an American television writer and producer best known for creating influential Western and adventure series during the mid-20th century.
  • B. Paul Ross
    Paul Ross is a British television and radio presenter known for his work on various UK talk and game shows and for being the brother of broadcaster Jonathan Ross.
  • C. Don Fletcher
    Don Fletcher is a writer best known for his work on the song "Dancing Machine."
  • D. Michael Morrow
    Michael Morrow is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the surname Morrow.
  • E. Anthony Gorry
    Anthony Gorry is a music producer known for his work on projects such as No Doubt’s album "Push and Shove."
  • 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: Lee Roberts
Triple: [Cokie Roberts, hasChild, Lee Roberts]
Generated description
Lee Roberts is a child of the late American journalist and political commentator Cokie Roberts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lee Roberts
Target entity description: Lee Roberts is a child of the late American journalist and political commentator Cokie Roberts.
  • A. Sam Rolfe
    Sam Rolfe was an American television writer and producer best known for creating influential Western and adventure series during the mid-20th century.
  • B. Paul Ross
    Paul Ross is a British television and radio presenter known for his work on various UK talk and game shows and for being the brother of broadcaster Jonathan Ross.
  • C. Don Fletcher
    Don Fletcher is a writer best known for his work on the song "Dancing Machine."
  • D. Michael Morrow
    Michael Morrow is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the surname Morrow.
  • E. Anthony Gorry
    Anthony Gorry is a music producer known for his work on projects such as No Doubt’s album "Push and Shove."
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15764d3a48190af79ce4642b7f563 completed April 29, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b3d420ce88190917c000b08d011df completed May 18, 2026, 4:24 p.m.
NEDg Description generation batch_6a0b416f94b88190b5bdc34752843ae2 completed May 18, 2026, 4:42 p.m.
NED2 Entity disambiguation (via description) batch_6a0b41db5d6481908dcd88d1c3376aae completed May 18, 2026, 4:44 p.m.
Created at: April 16, 2026, 8:42 p.m.