Triple

T2798030
Position Surface form Disambiguated ID Type / Status
Subject Walker Evans E53084 entity
Predicate spouse P13 FINISHED
Object Jane Ninas Evans
Jane Ninas Evans was the wife of renowned American photographer Walker Evans and a figure associated with his personal and artistic life.
E298376 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: Jane Ninas Evans | Statement: [Walker Evans, spouse, Jane Ninas Evans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Ninas Evans
Context triple: [Walker Evans, spouse, Jane Ninas Evans]
  • A. Gladys Louise Smith
    Gladys Louise Smith is the birth name of Mary Pickford, the pioneering Canadian-American silent film actress and producer known as "America's Sweetheart."
  • B. Ruth Josephine Googins
    Ruth Josephine Googins was the first wife of Elliott Roosevelt, son of U.S. President Franklin D. Roosevelt and Eleanor Roosevelt.
  • C. Margaret Ann Dixon
    Margaret Ann Dixon is best known as the wife of acclaimed Canadian film director and producer Norman Jewison.
  • D. Evangeline Johnson
    Evangeline Johnson was a member of the prominent Johnson family associated with the founding of Johnson & Johnson.
  • E. Ella Smith
    Ella Smith is a British actress known for her work in theatre, including a role in the National Theatre production of "Frankenstein," as well as in film and television.
  • 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: Jane Ninas Evans
Triple: [Walker Evans, spouse, Jane Ninas Evans]
Generated description
Jane Ninas Evans was the wife of renowned American photographer Walker Evans and a figure associated with his personal and artistic life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jane Ninas Evans
Target entity description: Jane Ninas Evans was the wife of renowned American photographer Walker Evans and a figure associated with his personal and artistic life.
  • A. Gladys Louise Smith
    Gladys Louise Smith is the birth name of Mary Pickford, the pioneering Canadian-American silent film actress and producer known as "America's Sweetheart."
  • B. Ruth Josephine Googins
    Ruth Josephine Googins was the first wife of Elliott Roosevelt, son of U.S. President Franklin D. Roosevelt and Eleanor Roosevelt.
  • C. Margaret Ann Dixon
    Margaret Ann Dixon is best known as the wife of acclaimed Canadian film director and producer Norman Jewison.
  • D. Evangeline Johnson
    Evangeline Johnson was a member of the prominent Johnson family associated with the founding of Johnson & Johnson.
  • E. Ella Smith
    Ella Smith is a British actress known for her work in theatre, including a role in the National Theatre production of "Frankenstein," as well as in film and television.
  • 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_69ab495a90788190941b6917e1eca3a6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abddf204148190a53f3f30d645d94c completed March 7, 2026, 8:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc66798148190bd7b163043167409 completed March 10, 2026, 7:21 a.m.
NEDg Description generation batch_69afc6e808708190a6fecd30f47d7e5a completed March 10, 2026, 7:23 a.m.
NED2 Entity disambiguation (via description) batch_69afc766c2508190af1d598eb18d38f7 completed March 10, 2026, 7:25 a.m.
Created at: March 6, 2026, 9:58 p.m.