Triple

T12239824
Position Surface form Disambiguated ID Type / Status
Subject Eva Marie Saint E291699 entity
Predicate spouse P13 FINISHED
Object Jeffrey Hayden
Jeffrey Hayden was an American television and film director known for his extensive work in mid-20th-century TV dramas and variety shows.
E1031870 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 Hayden | Statement: [Eva Marie Saint, spouse, Jeffrey Hayden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeffrey Hayden
Context triple: [Eva Marie Saint, spouse, Jeffrey Hayden]
  • A. Jeffrey Heath
    Jeffrey Heath is a linguist renowned for his extensive fieldwork and documentation of Dogon and other African languages.
  • B. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • C. Jeffrey Lynn
    Jeffrey Lynn was an American film and stage actor best known for his roles in 1930s and 1940s Hollywood dramas and romances.
  • D. Greg Hayden
    Greg Hayden is a film editor best known for his work on major comedy features, including the Austin Powers series.
  • E. Jay Hayden
    Jay Hayden is an American actor best known for his role as firefighter Travis Montgomery on the television drama series "Station 19."
  • 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 Hayden
Triple: [Eva Marie Saint, spouse, Jeffrey Hayden]
Generated description
Jeffrey Hayden was an American television and film director known for his extensive work in mid-20th-century TV dramas and variety shows.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jeffrey Hayden
Target entity description: Jeffrey Hayden was an American television and film director known for his extensive work in mid-20th-century TV dramas and variety shows.
  • A. Jeffrey Heath
    Jeffrey Heath is a linguist renowned for his extensive fieldwork and documentation of Dogon and other African languages.
  • B. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • C. Jeffrey Lynn
    Jeffrey Lynn was an American film and stage actor best known for his roles in 1930s and 1940s Hollywood dramas and romances.
  • D. Greg Hayden
    Greg Hayden is a film editor best known for his work on major comedy features, including the Austin Powers series.
  • E. Jay Hayden
    Jay Hayden is an American actor best known for his role as firefighter Travis Montgomery on the television drama series "Station 19."
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cb45340819093365f8efdf85f75 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f716afa8008190b4c518dd6004d87a completed May 3, 2026, 9:34 a.m.
NEDg Description generation batch_69f7179da5488190a10acadbf60ea470 completed May 3, 2026, 9:38 a.m.
NED2 Entity disambiguation (via description) batch_69f71847e7308190ac6f59a7dcafa452 completed May 3, 2026, 9:41 a.m.
Created at: April 8, 2026, 9:51 p.m.