Triple

T19627838
Position Surface form Disambiguated ID Type / Status
Subject 3000 Miles to Graceland E471183 entity
Predicate hasCharacter P2308 FINISHED
Object Thomas J. Murphy
Thomas J. Murphy is a fictional character from the crime action film "3000 Miles to Graceland."
 E1415612 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: Thomas J. Murphy | Statement: [3000 Miles to Graceland, hasCharacter, Thomas J. Murphy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Thomas J. Murphy
Context triple: [3000 Miles to Graceland, hasCharacter, Thomas J. Murphy]
  • A. John A. Murphy
    John A. Murphy was a prominent Irish historian and long-serving senator known for his work on modern Irish history and his outspoken contributions to public debate.
  • B. Cornelius J. Sullivan
    Cornelius J. Sullivan was an American lawyer and art collector active in early 20th-century New York cultural circles.
  • C. John P. Harrington
    John P. Harrington is an American writer best known as the author of the novel "Encounter with an Angry God."
  • D. John C. Dugan
    John C. Dugan is an American lawyer and former U.S. Comptroller of the Currency who has held prominent regulatory and leadership roles in the financial services industry.
  • E. Thomas A. Muldoon
    Thomas A. Muldoon is a film editor known for his work on the action-comedy movie "Pain & Gain."
  • 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: Thomas J. Murphy
Triple: [3000 Miles to Graceland, hasCharacter, Thomas J. Murphy]
Generated description
Thomas J. Murphy is a fictional character from the crime action film "3000 Miles to Graceland."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Thomas J. Murphy
Target entity description: Thomas J. Murphy is a fictional character from the crime action film "3000 Miles to Graceland."
  • A. John A. Murphy
    John A. Murphy was a prominent Irish historian and long-serving senator known for his work on modern Irish history and his outspoken contributions to public debate.
  • B. Cornelius J. Sullivan
    Cornelius J. Sullivan was an American lawyer and art collector active in early 20th-century New York cultural circles.
  • C. John P. Harrington
    John P. Harrington is an American writer best known as the author of the novel "Encounter with an Angry God."
  • D. John C. Dugan
    John C. Dugan is an American lawyer and former U.S. Comptroller of the Currency who has held prominent regulatory and leadership roles in the financial services industry.
  • E. Thomas A. Muldoon
    Thomas A. Muldoon is a film editor known for his work on the action-comedy movie "Pain & Gain."
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e641007e5881908da78e50aa36f340 completed April 20, 2026, 3:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a083c5efa4c8190879fde20322590f5 completed May 16, 2026, 9:43 a.m.
NEDg Description generation batch_6a083cc663d48190883c1d255ca426e9 completed May 16, 2026, 9:45 a.m.
NED2 Entity disambiguation (via description) batch_6a083d57e2bc8190826328935e16f335 completed May 16, 2026, 9:48 a.m.
Created at: April 10, 2026, 1:44 p.m.