Triple

T9789914
Position Surface form Disambiguated ID Type / Status
Subject Homefront E237580 entity
Predicate editedBy P1954 FINISHED
Object Padraic McKinley
Padraic McKinley is a film editor best known for his work on the action thriller movie "Homefront."
E849390 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: Padraic McKinley | Statement: [Homefront, editedBy, Padraic McKinley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Padraic McKinley
Context triple: [Homefront, editedBy, Padraic McKinley]
  • A. John O'Brien
    John O'Brien is an American screenwriter best known for co-writing the 2004 film adaptation of the classic television series "Starsky & Hutch."
  • B. George Tierney
    George Tierney was a prominent late 18th- and early 19th-century British Whig politician known for his opposition to William Pitt the Younger and his role as a leading parliamentary critic of government policy.
  • C. Patrick Flanagan
    Patrick Flanagan is an American inventor and author best known for his work on neurophone technology and fringe scientific and New Age concepts.
  • D. Angus O'Connor
    Angus O'Connor is a fictional character portrayed by Scottish actor Clive Russell.
  • E. Brian Kavanagh
    Brian Kavanagh is a film editor best known for his work on notable Australian and international films, including the drama "The Devil's Playground."
  • 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: Padraic McKinley
Triple: [Homefront, editedBy, Padraic McKinley]
Generated description
Padraic McKinley is a film editor best known for his work on the action thriller movie "Homefront."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Padraic McKinley
Target entity description: Padraic McKinley is a film editor best known for his work on the action thriller movie "Homefront."
  • A. John O'Brien
    John O'Brien is an American screenwriter best known for co-writing the 2004 film adaptation of the classic television series "Starsky & Hutch."
  • B. George Tierney
    George Tierney was a prominent late 18th- and early 19th-century British Whig politician known for his opposition to William Pitt the Younger and his role as a leading parliamentary critic of government policy.
  • C. Patrick Flanagan
    Patrick Flanagan is an American inventor and author best known for his work on neurophone technology and fringe scientific and New Age concepts.
  • D. Angus O'Connor
    Angus O'Connor is a fictional character portrayed by Scottish actor Clive Russell.
  • E. Brian Kavanagh
    Brian Kavanagh is a film editor best known for his work on notable Australian and international films, including the drama "The Devil's Playground."
  • 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_69ca84dc04488190b9c91193976c0960 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda214875481909f39e1d4dbac1fdb completed April 1, 2026, 10:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69d6525a4af08190bcd8455e95a2f3ae completed April 8, 2026, 1:04 p.m.
NEDg Description generation batch_69d65348c988819083f4c8008a1f8cf7 completed April 8, 2026, 1:08 p.m.
NED2 Entity disambiguation (via description) batch_69d654b44070819098e1148e9dbd8a11 completed April 8, 2026, 1:14 p.m.
Created at: March 30, 2026, 8:28 p.m.