Triple

T14965828
Position Surface form Disambiguated ID Type / Status
Subject Esurance E373184 entity
Predicate foundedBy P104 FINISHED
Object Jeffrey Goodman
Jeffrey Goodman is an entrepreneur best known as a founder of the online auto insurance company Esurance.
 E1209375 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: Jeffrey Goodman | Statement: [Esurance, foundedBy, Jeffrey Goodman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jeffrey Goodman
Context triple: [Esurance, foundedBy, Jeffrey Goodman]
  • A. Josh Kesselman
    Josh Kesselman is a film and television producer best known for his work as an executive producer on projects such as the series "The Great."
  • B. Brian Goodman
    Brian Goodman is an American actor and director known for his character roles in film and television, including a notable part in the crime drama series "Rizzoli & Isles."
  • C. Clancy Sigal
    Clancy Sigal was an American novelist, memoirist, and screenwriter known for his politically charged writing and his involvement in mid-20th-century leftist and literary circles.
  • D. Jeffrey Cohen
    Jeffrey Cohen is a songwriter best known for co-writing the theme song to the James Bond film "Licence to Kill."
  • E. Sam Greisman
    Sam Greisman is an American writer and director known publicly as the son of acclaimed actress Sally Field.
  • 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: Jeffrey Goodman
Triple: [Esurance, foundedBy, Jeffrey Goodman]
Generated description
Jeffrey Goodman is an entrepreneur best known as a founder of the online auto insurance company Esurance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jeffrey Goodman
Target entity description: Jeffrey Goodman is an entrepreneur best known as a founder of the online auto insurance company Esurance.
  • A. Josh Kesselman
    Josh Kesselman is a film and television producer best known for his work as an executive producer on projects such as the series "The Great."
  • B. Brian Goodman
    Brian Goodman is an American actor and director known for his character roles in film and television, including a notable part in the crime drama series "Rizzoli & Isles."
  • C. Clancy Sigal
    Clancy Sigal was an American novelist, memoirist, and screenwriter known for his politically charged writing and his involvement in mid-20th-century leftist and literary circles.
  • D. Jeffrey Cohen
    Jeffrey Cohen is a songwriter best known for co-writing the theme song to the James Bond film "Licence to Kill."
  • E. Sam Greisman
    Sam Greisman is an American writer and director known publicly as the son of acclaimed actress Sally Field.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e2fdcc8190bffe603db3388736 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002d92c9788190aa4523a1e47bc561 completed May 10, 2026, 7:02 a.m.
NEDg Description generation batch_6a00305c62d0819092d06963e09d51fc completed May 10, 2026, 7:14 a.m.
NED2 Entity disambiguation (via description) batch_6a0030e12bd08190aa101634c88e37e7 completed May 10, 2026, 7:16 a.m.
Created at: April 10, 2026, 2:47 a.m.