Triple

T1564444
Position Surface form Disambiguated ID Type / Status
Subject Hal Holbrook E33399 entity
Predicate spouse P13 FINISHED
Object Carol Eve Rossen
Carol Eve Rossen is an American actress known for her work in film and television and for her former marriage to actor Hal Holbrook.
E219815 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: Carol Eve Rossen | Statement: [Hal Holbrook, spouse, Carol Eve Rossen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Eve Rossen
Context triple: [Hal Holbrook, spouse, Carol Eve Rossen]
  • A. Doris Neustadt
    Doris Neustadt was a benefactor and namesake of the prestigious Neustadt International Prize for Literature, recognized for her support of literary arts.
  • B. Marjorie Leonard Brennan
    Marjorie Leonard Brennan was the wife of U.S. Supreme Court Justice William J. Brennan Jr.
  • C. Barbara Robbins
    Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
  • D. Esther Bubley
    Esther Bubley was an American documentary photographer best known for her intimate, human-centered images of everyday life in mid-20th-century America, particularly during and after World War II.
  • E. Patricia Russo
    Patricia Russo is an American business executive best known for serving as CEO of Lucent Technologies and later Alcatel-Lucent.
  • 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: Carol Eve Rossen
Triple: [Hal Holbrook, spouse, Carol Eve Rossen]
Generated description
Carol Eve Rossen is an American actress known for her work in film and television and for her former marriage to actor Hal Holbrook.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carol Eve Rossen
Target entity description: Carol Eve Rossen is an American actress known for her work in film and television and for her former marriage to actor Hal Holbrook.
  • A. Doris Neustadt
    Doris Neustadt was a benefactor and namesake of the prestigious Neustadt International Prize for Literature, recognized for her support of literary arts.
  • B. Marjorie Leonard Brennan
    Marjorie Leonard Brennan was the wife of U.S. Supreme Court Justice William J. Brennan Jr.
  • C. Barbara Robbins
    Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
  • D. Esther Bubley
    Esther Bubley was an American documentary photographer best known for her intimate, human-centered images of everyday life in mid-20th-century America, particularly during and after World War II.
  • E. Patricia Russo
    Patricia Russo is an American business executive best known for serving as CEO of Lucent Technologies and later Alcatel-Lucent.
  • 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_69a885f11b048190935025a035302715 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa621242188190a7e1deeada7688d8 completed March 6, 2026, 5:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfb90e16081908d70df182b7efb8a completed March 8, 2026, 10:43 p.m.
NEDg Description generation batch_69adfc81697c8190b0dd847649f28923 completed March 8, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69adfdc8a7f481909b2ee0b4444cf4b9 completed March 8, 2026, 10:52 p.m.
Created at: March 4, 2026, 7:27 p.m.