Triple

T15835564
Position Surface form Disambiguated ID Type / Status
Subject Carol Browner E383974 entity
Predicate spouse P13 FINISHED
Object Tom Downey
Tom Downey is a former U.S. Congressman from New York who later became a prominent lobbyist and policy consultant.
 E1180470 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: Tom Downey | Statement: [Carol Browner, spouse, Tom Downey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom Downey
Context triple: [Carol Browner, spouse, Tom Downey]
  • A. Bill DeMott
    Bill DeMott is a retired American professional wrestler and wrestling trainer best known for his work in World Championship Wrestling (WCW) and WWE, including a controversial tenure as head trainer for WWE’s developmental system.
  • B. Chub Feeney
    Chub Feeney was a longtime Major League Baseball executive who served as president of the National League from 1970 to 1986.
  • C. David Owen Dodd
    David Owen Dodd was a Confederate courier during the American Civil War who was executed as a spy at age 17 and later became known as the “Boy Hero of the Confederacy.”
  • D. Edward McDonnell
    Edward McDonnell is a film producer known for his work on movies such as the psychological thriller "Insomnia" (2002).
  • E. Edward McDonnell
    Edward McDonnell is a film producer known for his work on movies such as "Teaching Mrs. Tingle."
  • 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: Tom Downey
Triple: [Carol Browner, spouse, Tom Downey]
Generated description
Tom Downey is a former U.S. Congressman from New York who later became a prominent lobbyist and policy consultant.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom Downey
Target entity description: Tom Downey is a former U.S. Congressman from New York who later became a prominent lobbyist and policy consultant.
  • A. Bill DeMott
    Bill DeMott is a retired American professional wrestler and wrestling trainer best known for his work in World Championship Wrestling (WCW) and WWE, including a controversial tenure as head trainer for WWE’s developmental system.
  • B. Chub Feeney
    Chub Feeney was a longtime Major League Baseball executive who served as president of the National League from 1970 to 1986.
  • C. David Owen Dodd
    David Owen Dodd was a Confederate courier during the American Civil War who was executed as a spy at age 17 and later became known as the “Boy Hero of the Confederacy.”
  • D. Edward McDonnell
    Edward McDonnell is a film producer known for his work on movies such as "Teaching Mrs. Tingle."
  • E. Edward McDonnell
    Edward McDonnell is a film producer known for his work on movies such as the psychological thriller "Insomnia" (2002).
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e0e1cc8190851b30b03cf9c9b8 completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa137be2c81909c8f04b5cc1a5b21 completed May 9, 2026, 9:03 p.m.
NEDg Description generation batch_69ffa527af048190b1f87d85e50bf254 completed May 9, 2026, 9:20 p.m.
NED2 Entity disambiguation (via description) batch_69ffa5df00e481909e203e78940395ed completed May 9, 2026, 9:23 p.m.
Created at: April 10, 2026, 4:49 a.m.