Triple

T2951849
Position Surface form Disambiguated ID Type / Status
Subject GEICO E79837 entity
Predicate founders P104 FINISHED
Object Lillian Goodwin
Lillian Goodwin was an American businesswoman who co-founded the auto insurance company GEICO with her husband Leo Goodwin in the 1930s.
E516918 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: Lillian Goodwin | Statement: [GEICO, founders, Lillian Goodwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lillian Goodwin
Context triple: [GEICO, founders, Lillian Goodwin]
  • A. Lilian Greenwood
    Lilian Greenwood is a British Labour Party politician who has served as the Member of Parliament for Nottingham South since 2010 and has held various frontbench and committee roles.
  • B. Ethel Gross
    Ethel Gross was the first wife of Harry Hopkins, a key advisor to U.S. President Franklin D. Roosevelt.
  • C. Ethel Wayman
    Ethel Wayman was the wife of British humorist and novelist P. G. Wodehouse.
  • D. Louise Treadwell
    Louise Treadwell was an American actress and philanthropist best known as the longtime wife of actor Spencer Tracy and co-founder of the John Tracy Clinic for children with hearing impairments.
  • E. Edna May Oliver
    Edna May Oliver was an American character actress known for her sharp-tongued, comedic roles in 1930s Hollywood films and her distinctive, austere appearance.
  • 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: Lillian Goodwin
Triple: [GEICO, founders, Lillian Goodwin]
Generated description
Lillian Goodwin was an American businesswoman who co-founded the auto insurance company GEICO with her husband Leo Goodwin in the 1930s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lillian Goodwin
Target entity description: Lillian Goodwin was an American businesswoman who co-founded the auto insurance company GEICO with her husband Leo Goodwin in the 1930s.
  • A. Lilian Greenwood
    Lilian Greenwood is a British Labour Party politician who has served as the Member of Parliament for Nottingham South since 2010 and has held various frontbench and committee roles.
  • B. Ethel Gross
    Ethel Gross was the first wife of Harry Hopkins, a key advisor to U.S. President Franklin D. Roosevelt.
  • C. Ethel Wayman
    Ethel Wayman was the wife of British humorist and novelist P. G. Wodehouse.
  • D. Louise Treadwell
    Louise Treadwell was an American actress and philanthropist best known as the longtime wife of actor Spencer Tracy and co-founder of the John Tracy Clinic for children with hearing impairments.
  • E. Edna May Oliver
    Edna May Oliver was an American character actress known for her sharp-tongued, comedic roles in 1930s Hollywood films and her distinctive, austere appearance.
  • 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_69ad8b1276588190a374a0b12e0f7bdf completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad98fcea5c8190b7d80de942bcb4f7 completed March 8, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf32e44ed88190a7a6d9ea9097d8e6 completed March 22, 2026, 12:08 a.m.
NEDg Description generation batch_69bf3485cfac81909c4868842fc0949f completed March 22, 2026, 12:15 a.m.
NED2 Entity disambiguation (via description) batch_69bf34e3161881908dbf77118fda3824 completed March 22, 2026, 12:16 a.m.
Created at: March 8, 2026, 2:57 p.m.