Triple

T9097424
Position Surface form Disambiguated ID Type / Status
Subject Louis Prima E218061 entity
Predicate spouse P13 FINISHED
Object Alma Ross
Alma Ross was one of the early wives of famed American jazz and swing musician Louis Prima.
E796137 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: Alma Ross | Statement: [Louis Prima, spouse, Alma Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alma Ross
Context triple: [Louis Prima, spouse, Alma Ross]
  • A. Myrna Fahey
    Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
  • B. Alyce Mayo
    Alyce Mayo is an American actress and former wife of acclaimed actor Peter Falk.
  • C. Eileen Baker
    Eileen Baker is best known as the wife of English actor Kenny Baker, who famously portrayed R2-D2 in the original Star Wars films.
  • D. Marguerite Roberts
    Marguerite Roberts was a prominent American screenwriter known for her sharp dialogue and work on numerous Hollywood films from the 1930s through the 1960s, including the classic Western "True Grit."
  • E. Maxine Albro
    Maxine Albro was an American muralist and painter associated with the New Deal era, best known for her vibrant frescoes and contributions to public art in San Francisco.
  • 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: Alma Ross
Triple: [Louis Prima, spouse, Alma Ross]
Generated description
Alma Ross was one of the early wives of famed American jazz and swing musician Louis Prima.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alma Ross
Target entity description: Alma Ross was one of the early wives of famed American jazz and swing musician Louis Prima.
  • A. Myrna Fahey
    Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
  • B. Alyce Mayo
    Alyce Mayo is an American actress and former wife of acclaimed actor Peter Falk.
  • C. Eileen Baker
    Eileen Baker is best known as the wife of English actor Kenny Baker, who famously portrayed R2-D2 in the original Star Wars films.
  • D. Marguerite Roberts
    Marguerite Roberts was a prominent American screenwriter known for her sharp dialogue and work on numerous Hollywood films from the 1930s through the 1960s, including the classic Western "True Grit."
  • E. Maxine Albro
    Maxine Albro was an American muralist and painter associated with the New Deal era, best known for her vibrant frescoes and contributions to public art in San Francisco.
  • 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_69ca83d9844081908e561e367fda6d45 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc96b7d0d48190a3b15f35bef087e3 completed April 1, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69d100b451c88190aae0ef240906ce0c completed April 4, 2026, 12:14 p.m.
NEDg Description generation batch_69d1025c68408190b5f2e23d7a2f2221 completed April 4, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_69d102b154f88190b13868ce5df59510 completed April 4, 2026, 12:23 p.m.
Created at: March 30, 2026, 7:15 p.m.