Triple

T7853574
Position Surface form Disambiguated ID Type / Status
Subject Van Johnson E182115 entity
Predicate spouse P13 FINISHED
Object Evangeline Johnson
Evangeline Johnson was the wife of American film and television actor Van Johnson.
E717657 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: Evangeline Johnson | Statement: [Van Johnson, spouse, Evangeline Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evangeline Johnson
Context triple: [Van Johnson, spouse, Evangeline Johnson]
  • A. Evangeline Johnson
    Evangeline Johnson was a member of the prominent Johnson family associated with the founding of Johnson & Johnson.
  • B. Vickie Johnson
    Vickie Johnson is a former WNBA guard and experienced professional basketball coach who has led multiple teams in the league.
  • C. Carmen Johnson
    Carmen Johnson is a member of the Johnson family best known through her father, American sportscaster Ernie Johnson Jr.
  • D. Francesca Johnson
    Francesca Johnson is the introspective Italian-American farm wife whose brief, life-altering love affair lies at the emotional core of the romantic drama "The Bridges of Madison County."
  • E. Jeanne Johnson
    Jeanne Johnson is known as the wife of American actor and voice actor Clancy Brown.
  • 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: Evangeline Johnson
Triple: [Van Johnson, spouse, Evangeline Johnson]
Generated description
Evangeline Johnson was the wife of American film and television actor Van Johnson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Evangeline Johnson
Target entity description: Evangeline Johnson was the wife of American film and television actor Van Johnson.
  • A. Evangeline Johnson
    Evangeline Johnson was a member of the prominent Johnson family associated with the founding of Johnson & Johnson.
  • B. Vickie Johnson
    Vickie Johnson is a former WNBA guard and experienced professional basketball coach who has led multiple teams in the league.
  • C. Carmen Johnson
    Carmen Johnson is a member of the Johnson family best known through her father, American sportscaster Ernie Johnson Jr.
  • D. Francesca Johnson
    Francesca Johnson is the introspective Italian-American farm wife whose brief, life-altering love affair lies at the emotional core of the romantic drama "The Bridges of Madison County."
  • E. Jeanne Johnson
    Jeanne Johnson is known as the wife of American actor and voice actor Clancy Brown.
  • 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_69ca82869ee08190b8f9040dbc2c0467 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb18ed56d481909266d862e0ae152d completed March 31, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccec5f00b48190b35f7cab67e7e5f9 completed April 1, 2026, 9:58 a.m.
NEDg Description generation batch_69ccf0982f4481908e2a59424fdf470f completed April 1, 2026, 10:16 a.m.
NED2 Entity disambiguation (via description) batch_69cd051913708190a83f925cf0cbbaa1 completed April 1, 2026, 11:44 a.m.
Created at: March 30, 2026, 4:51 p.m.