Triple

T11464867
Position Surface form Disambiguated ID Type / Status
Subject Show People E271753 entity
Predicate starred P5563 FINISHED
Object Paul Ralli
Paul Ralli was an actor known for his role in the 1928 film "Show People" and other early Hollywood productions.
E937943 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: Paul Ralli | Statement: [Show People, starred, Paul Ralli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Ralli
Context triple: [Show People, starred, Paul Ralli]
  • A. Joe Guyon
    Joe Guyon was a Pro Football Hall of Fame halfback and tackle from the early 20th century, known for his standout college career and success in the nascent years of the NFL.
  • B. Michael Goudeau
    Michael Goudeau is an American juggler, comedian, and writer best known for his long-running collaboration with magician Penn Jillette on stage shows and media projects.
  • C. Jean-Pierre Duprey
    Jean-Pierre Duprey was a French surrealist poet, sculptor, and painter associated with the postwar Surrealist movement in Paris.
  • D. Guy Billout
    Guy Billout is a French illustrator and graphic artist renowned for his surreal, meticulously detailed illustrations that often feature ironic or thought-provoking twists.
  • E. Jean-Claude Olivier
    Jean-Claude Olivier is a writer associated with the Juicy brand or publication.
  • 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: Paul Ralli
Triple: [Show People, starred, Paul Ralli]
Generated description
Paul Ralli was an actor known for his role in the 1928 film "Show People" and other early Hollywood productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paul Ralli
Target entity description: Paul Ralli was an actor known for his role in the 1928 film "Show People" and other early Hollywood productions.
  • A. Joe Guyon
    Joe Guyon was a Pro Football Hall of Fame halfback and tackle from the early 20th century, known for his standout college career and success in the nascent years of the NFL.
  • B. Michael Goudeau
    Michael Goudeau is an American juggler, comedian, and writer best known for his long-running collaboration with magician Penn Jillette on stage shows and media projects.
  • C. Jean-Pierre Duprey
    Jean-Pierre Duprey was a French surrealist poet, sculptor, and painter associated with the postwar Surrealist movement in Paris.
  • D. Guy Billout
    Guy Billout is a French illustrator and graphic artist renowned for his surreal, meticulously detailed illustrations that often feature ironic or thought-provoking twists.
  • E. Jean-Claude Olivier
    Jean-Claude Olivier is a writer associated with the Juicy brand or publication.
  • 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_69d6aae0c8d881908a5a360c0be3242e completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d822f5eb988190b309b8e309f6d1a5 completed April 9, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69ee866bb71c819091573965f7cf0dee completed April 26, 2026, 9:40 p.m.
NEDg Description generation batch_69eeb310e04c8190a1004662d5bbc015 completed April 27, 2026, 12:51 a.m.
NED2 Entity disambiguation (via description) batch_69eee95dfff48190a3c3022cdfc6dafc completed April 27, 2026, 4:43 a.m.
Created at: April 8, 2026, 9:35 p.m.