Triple

T11464586
Position Surface form Disambiguated ID Type / Status
Subject The Big Parade E271747 entity
Predicate starring P1507 FINISHED
Object Tom O’Brien
Tom O’Brien was an American actor best known for his roles in silent-era films, including prominent appearances in major 1920s productions.
 E956466 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: Tom O’Brien | Statement: [The Big Parade, starring, Tom O’Brien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom O’Brien
Context triple: [The Big Parade, starring, Tom O’Brien]
  • A. Tom O’Brien
    Tom O’Brien is an American football coach best known for revitalizing Boston College’s football program in the late 1990s and early 2000s before later leading NC State.
  • B. Tom O'Brien
    Tom O'Brien is a media executive and broadcaster best known for his leadership and on-air roles at The Weather Channel.
  • C. John M. Keane
    John M. Keane is a television and film composer best known for scoring crime drama series such as CSI: Vegas.
  • D. John E. Keane
    John E. Keane is a composer best known for his work on film and television scores, including the adaptation of "Wives and Daughters."
  • E. Brian Moynihan
    Brian Moynihan is an American lawyer and businessman who serves as the longtime chairman and chief executive officer of Bank of America.
  • 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: Tom O’Brien
Triple: [The Big Parade, starring, Tom O’Brien]
Generated description
Tom O’Brien was an American actor best known for his roles in silent-era films, including prominent appearances in major 1920s productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom O’Brien
Target entity description: Tom O’Brien was an American actor best known for his roles in silent-era films, including prominent appearances in major 1920s productions.
  • A. Tom O’Brien
    Tom O’Brien is an American football coach best known for revitalizing Boston College’s football program in the late 1990s and early 2000s before later leading NC State.
  • B. Tom O'Brien
    Tom O'Brien is a media executive and broadcaster best known for his leadership and on-air roles at The Weather Channel.
  • C. John M. Keane
    John M. Keane is a television and film composer best known for scoring crime drama series such as CSI: Vegas.
  • D. John E. Keane
    John E. Keane is a composer best known for his work on film and television scores, including the adaptation of "Wives and Daughters."
  • E. Brian Moynihan
    Brian Moynihan is an American lawyer and businessman who serves as the longtime chairman and chief executive officer of Bank of America.
  • 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_69d822f488248190b9f603cd31c72174 completed April 9, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f457b970b88190869cb0b80aca5c4a completed May 1, 2026, 7:35 a.m.
NEDg Description generation batch_69f45f86349c81909a806fd7be4008e9 completed May 1, 2026, 8:08 a.m.
NED2 Entity disambiguation (via description) batch_69f4647ee1748190975bce3bbf51a3bc completed May 1, 2026, 8:29 a.m.
Created at: April 8, 2026, 9:35 p.m.