Triple

T14409678
Position Surface form Disambiguated ID Type / Status
Subject Mask Off E357290 entity
Predicate writer P1360 FINISHED
Object Tommy Butler
Tommy Butler is a writer best known for his work on the television series "Mask Off."
E1098073 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: Tommy Butler | Statement: [Mask Off, writer, Tommy Butler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tommy Butler
Context triple: [Mask Off, writer, Tommy Butler]
  • A. Joe Butler
    Joe Butler is a film editor best known for his work on the animated feature "Ron’s Gone Wrong."
  • B. Tommy Warrilow
    Tommy Warrilow is an English football manager and former player best known for managing non-league clubs, including a spell in charge of Ashford United F.C.
  • C. Tommy Cowling
    Tommy Cowling is a member of the group or team known as The Warriors.
  • D. Tommy Beresford
    Tommy Beresford is a fictional amateur detective and adventurer who, alongside his wife Tuppence, stars in several of Agatha Christie's mystery novels and short stories.
  • E. Tommy McClelland
    Tommy McClelland is a collegiate athletics administrator known for serving as the athletic director at Rice University and previously holding the same role at Louisiana Tech.
  • 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: Tommy Butler
Triple: [Mask Off, writer, Tommy Butler]
Generated description
Tommy Butler is a writer best known for his work on the television series "Mask Off."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tommy Butler
Target entity description: Tommy Butler is a writer best known for his work on the television series "Mask Off."
  • A. Joe Butler
    Joe Butler is a film editor best known for his work on the animated feature "Ron’s Gone Wrong."
  • B. Tommy Warrilow
    Tommy Warrilow is an English football manager and former player best known for managing non-league clubs, including a spell in charge of Ashford United F.C.
  • C. Tommy Cowling
    Tommy Cowling is a member of the group or team known as The Warriors.
  • D. Tommy Beresford
    Tommy Beresford is a fictional amateur detective and adventurer who, alongside his wife Tuppence, stars in several of Agatha Christie's mystery novels and short stories.
  • E. Tommy McClelland
    Tommy McClelland is a collegiate athletics administrator known for serving as the athletic director at Rice University and previously holding the same role at Louisiana Tech.
  • 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90c9b3448190aec1608836a5e913 completed April 14, 2026, 7:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd55269d8c81909592277741a93db6 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd58216a8c8190b1fffcb670f15e16 completed May 8, 2026, 3:27 a.m.
NED2 Entity disambiguation (via description) batch_69fd589144b8819099aadef126b8728f completed May 8, 2026, 3:29 a.m.
Created at: April 10, 2026, 1:17 a.m.