Triple

T6283843
Position Surface form Disambiguated ID Type / Status
Subject J. Randy Taraborrelli E140846 entity
Predicate notableWork P4 FINISHED
Object Elizabeth
"Elizabeth" is a biographical work by J. Randy Taraborrelli that chronicles the life and career of actress Elizabeth Taylor.
E590755 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 | Statement: [J. Randy Taraborrelli, notableWork, Elizabeth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Context triple: [J. Randy Taraborrelli, notableWork, Elizabeth]
  • A. Elizabeth
    Elizabeth "Betty" Ford was the influential First Lady of the United States from 1974 to 1977, renowned for her advocacy on women's rights, breast cancer awareness, and addiction treatment.
  • B. Elizabeth
    Elizabeth is the middle name of Diane Elizabeth Dern, an individual likely known in relation to the Dern family.
  • C. Elizabeth
    Elizabeth is the birth name of American actress and singer Betty Hutton, a popular Hollywood star of the 1940s and 1950s.
  • D. Elizabeth
    Elizabeth is an alternate given name associated with Mary Surratt, the American boardinghouse owner convicted and executed for her role in the conspiracy to assassinate President Abraham Lincoln.
  • E. Elizabeth
    Elizabeth is the formal first name of Bess Truman, who served as First Lady of the United States as the wife of President Harry S. Truman.
  • 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
Triple: [J. Randy Taraborrelli, notableWork, Elizabeth]
Generated description
"Elizabeth" is a biographical work by J. Randy Taraborrelli that chronicles the life and career of actress Elizabeth Taylor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Target entity description: "Elizabeth" is a biographical work by J. Randy Taraborrelli that chronicles the life and career of actress Elizabeth Taylor.
  • A. Elizabeth
    "Elizabeth" is a 1998 historical drama film that chronicles the early reign of Queen Elizabeth I of England, starring Cate Blanchett in the title role.
  • B. Elizabeth
    Elizabeth is the birth name of American comedian, writer, and actress Tina Fey, known for her work on "Saturday Night Live" and "30 Rock."
  • C. Elizabeth
    Elizabeth is a biblical figure in the New Testament, known as the mother of John the Baptist and a relative of Mary, the mother of Jesus.
  • D. Elizabeth
    Elizabeth is the birth name of American actress and singer Betty Hutton, a popular Hollywood star of the 1940s and 1950s.
  • E. Elizabeth
    Elizabeth is the first name of Elizabeth Warren, a prominent American politician and U.S. senator from Massachusetts known for her work on consumer protection and economic inequality.
  • 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_69c008cd17c8819082b82d3fbeb68047 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063fb6b1c8190b19a674c18fc9c53 completed March 22, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6385c26f08190952d810a82b9236f completed March 27, 2026, 7:57 a.m.
NEDg Description generation batch_69c63b8ef91881909aa61754c123ac24 completed March 27, 2026, 8:10 a.m.
NED2 Entity disambiguation (via description) batch_69c63c067c648190b6f4ac822d038900 completed March 27, 2026, 8:12 a.m.
Created at: March 22, 2026, 4:26 p.m.