Triple

T8061372
Position Surface form Disambiguated ID Type / Status
Subject Dan Dailey E188127 entity
Predicate spouse P13 FINISHED
Object Elizabeth Dailey
Elizabeth Dailey is known primarily as the spouse of American actor and dancer Dan Dailey.
 E776855 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: Elizabeth Dailey | Statement: [Dan Dailey, spouse, Elizabeth Dailey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Dailey
Context triple: [Dan Dailey, spouse, Elizabeth Dailey]
  • A. Lisa Blount
    Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
  • B. Lisa Loring
    Lisa Loring was an American actress best known for originating the role of Wednesday Addams as a child in the 1960s television adaptation of The Addams Family.
  • C. Eileen Herlie
    Eileen Herlie was a Scottish-American actress best known for her classical stage work and prominent film and television roles, including notable Shakespearean performances.
  • D. Karen Richards
    Karen Richards is a fictional character from the 1949 play "Aged in Wood," likely serving as a central figure in its dramatic narrative.
  • E. Karen Richards
    Karen Richards is a television producer best known for her executive production work on the horror drama series "Penny Dreadful."
  • 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: Elizabeth Dailey
Triple: [Dan Dailey, spouse, Elizabeth Dailey]
Generated description
Elizabeth Dailey is known primarily as the spouse of American actor and dancer Dan Dailey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Dailey
Target entity description: Elizabeth Dailey is known primarily as the spouse of American actor and dancer Dan Dailey.
  • A. Lisa Blount
    Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
  • B. Lisa Loring
    Lisa Loring was an American actress best known for originating the role of Wednesday Addams as a child in the 1960s television adaptation of The Addams Family.
  • C. Eileen Herlie
    Eileen Herlie was a Scottish-American actress best known for her classical stage work and prominent film and television roles, including notable Shakespearean performances.
  • D. Karen Richards
    Karen Richards is a television producer best known for her executive production work on the horror drama series "Penny Dreadful."
  • E. Karen Richards
    Karen Richards is a fictional character from the 1949 play "Aged in Wood," likely serving as a central figure in its dramatic narrative.
  • 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_69ca82b2f68881908c50560697e210da completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3fcc61c0819085edc26e75c5f6d5 completed March 31, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d016a0027c81908d3454447fa461b2 completed April 3, 2026, 7:36 p.m.
NEDg Description generation batch_69d019059e8481909a696575366aa0b6 completed April 3, 2026, 7:46 p.m.
NED2 Entity disambiguation (via description) batch_69d019a2736c8190880c8f3786cf353b completed April 3, 2026, 7:48 p.m.
Created at: March 30, 2026, 5:26 p.m.