Triple

T13140207
Position Surface form Disambiguated ID Type / Status
Subject Brassed Off E312191 entity
Predicate editedBy P1954 FINISHED
Object Michael Ellis
Michael Ellis is a film editor best known for his work on the British comedy-drama film "Brassed Off."
E1024787 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: Michael Ellis | Statement: [Brassed Off, editedBy, Michael Ellis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Ellis
Context triple: [Brassed Off, editedBy, Michael Ellis]
  • A. Aaron Jeffery
    Aaron Jeffery is a New Zealand-born Australian actor best known for his roles in television dramas such as "McLeod's Daughters" and "Wentworth."
  • B. Charlie Jeffery
    Charlie Jeffery is a British political scientist and academic leader who serves as Vice-Chancellor of the University of York.
  • C. Charles Snodgrass
    Charles Snodgrass is a person notable enough to be recognized as a primary bearer of the surname Snodgrass.
  • D. D. J. Opperman
    D. J. Opperman was a prominent 20th-century Afrikaans poet and academic, widely regarded as one of the most influential figures in modern Afrikaans literature.
  • E. Mitchell Anderson
    Mitchell Anderson is an American actor best known for his film and television work in the 1980s and 1990s, including roles in projects like "Jaws: The Revenge" and the series "Party of Five."
  • 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: Michael Ellis
Triple: [Brassed Off, editedBy, Michael Ellis]
Generated description
Michael Ellis is a film editor best known for his work on the British comedy-drama film "Brassed Off."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Ellis
Target entity description: Michael Ellis is a film editor best known for his work on the British comedy-drama film "Brassed Off."
  • A. Aaron Jeffery
    Aaron Jeffery is a New Zealand-born Australian actor best known for his roles in television dramas such as "McLeod's Daughters" and "Wentworth."
  • B. Charlie Jeffery
    Charlie Jeffery is a British political scientist and academic leader who serves as Vice-Chancellor of the University of York.
  • C. Charles Snodgrass
    Charles Snodgrass is a person notable enough to be recognized as a primary bearer of the surname Snodgrass.
  • D. D. J. Opperman
    D. J. Opperman was a prominent 20th-century Afrikaans poet and academic, widely regarded as one of the most influential figures in modern Afrikaans literature.
  • E. Mitchell Anderson
    Mitchell Anderson is an American actor best known for his film and television work in the 1980s and 1990s, including roles in projects like "Jaws: The Revenge" and the series "Party of Five."
  • 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d981b84f1081908b9e2d54a64d4c2d completed April 10, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eae2c3848190b062fa8da7dc8a92 completed May 3, 2026, 6:27 a.m.
NEDg Description generation batch_69f6f01e9c488190ad52280903c074da completed May 3, 2026, 6:50 a.m.
NED2 Entity disambiguation (via description) batch_69f6f0e5f94c81908f4707913dc5dc92 completed May 3, 2026, 6:53 a.m.
Created at: April 9, 2026, 9:09 p.m.