Triple

T14841532
Position Surface form Disambiguated ID Type / Status
Subject Mitzi Gaynor E348975 entity
Predicate spouse P13 FINISHED
Object Jack Bean
Jack Bean was an American talent agent and film producer best known as the longtime husband and manager of actress and singer Mitzi Gaynor.
 E1121951 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: Jack Bean | Statement: [Mitzi Gaynor, spouse, Jack Bean]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jack Bean
Context triple: [Mitzi Gaynor, spouse, Jack Bean]
  • A. Andy Bean
    Andy Bean is an American actor best known for his roles in films like "It Chapter Two" and television series such as "Power" and "Here and Now."
  • B. Tom Bean
    Tom Bean was an early settler and landowner in Texas after whom the city of Tom Bean, Texas, is named.
  • C. Charlie Bean
    Charlie Bean is an American animator, storyboard artist, and film director known for his work on animated projects including co-directing *The Lego Ninjago Movie*.
  • D. Jim Beanz
    Jim Beanz is an American songwriter, vocal producer, and record producer known for his extensive work with Timbaland and contributions to numerous R&B and pop hits.
  • E. Paulie Bleeker
    Paulie Bleeker is a shy, sweet-natured high school track athlete and the awkward love interest of the title character in the film "Juno."
  • 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: Jack Bean
Triple: [Mitzi Gaynor, spouse, Jack Bean]
Generated description
Jack Bean was an American talent agent and film producer best known as the longtime husband and manager of actress and singer Mitzi Gaynor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jack Bean
Target entity description: Jack Bean was an American talent agent and film producer best known as the longtime husband and manager of actress and singer Mitzi Gaynor.
  • A. Andy Bean
    Andy Bean is an American actor best known for his roles in films like "It Chapter Two" and television series such as "Power" and "Here and Now."
  • B. Tom Bean
    Tom Bean was an early settler and landowner in Texas after whom the city of Tom Bean, Texas, is named.
  • C. Charlie Bean
    Charlie Bean is an American animator, storyboard artist, and film director known for his work on animated projects including co-directing *The Lego Ninjago Movie*.
  • D. Jim Beanz
    Jim Beanz is an American songwriter, vocal producer, and record producer known for his extensive work with Timbaland and contributions to numerous R&B and pop hits.
  • E. Paulie Bleeker
    Paulie Bleeker is a shy, sweet-natured high school track athlete and the awkward love interest of the title character in the film "Juno."
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded28fa49c81908d1059e6cafd607f completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe38a9eb9481908ca509f484007cf6 completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe3d0eca948190b107bc593b6e5b72 completed May 8, 2026, 7:44 p.m.
NED2 Entity disambiguation (via description) batch_69fe3d94785881908911a7c6f1546d45 completed May 8, 2026, 7:46 p.m.
Created at: April 10, 2026, 1:53 a.m.