Triple

T13481321
Position Surface form Disambiguated ID Type / Status
Subject Someone to Watch Over Me E318378 entity
Predicate mainCharacter P1183 FINISHED
Object Mike Keegan
Mike Keegan is the New York City police detective protagonist of the 1987 neo-noir thriller film "Someone to Watch Over Me."
E1119391 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: Mike Keegan | Statement: [Someone to Watch Over Me, mainCharacter, Mike Keegan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Keegan
Context triple: [Someone to Watch Over Me, mainCharacter, Mike Keegan]
  • A. Joe Kerrigan
    Joe Kerrigan is a former Major League Baseball pitching coach and brief Boston Red Sox manager best known for his long coaching career with several MLB teams.
  • B. Tom Keogh
    Tom Keogh was a noted costume designer best known for his work in mid-20th-century theatre and film productions.
  • C. Mick Burke
    Mick Burke was a renowned British mountaineer best known for his high-altitude climbs in the Himalayas and his work as a climbing cameraman on major expeditions.
  • D. Joe Keenan
    Joe Keenan is an American television writer, producer, and novelist best known for his work on the sitcom "Frasier" and other acclaimed comedy projects.
  • E. Kevin Duggan
    Kevin Duggan is a relatively obscure individual whose name is shared with multiple people across different professions, such as sports and public service.
  • 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: Mike Keegan
Triple: [Someone to Watch Over Me, mainCharacter, Mike Keegan]
Generated description
Mike Keegan is the New York City police detective protagonist of the 1987 neo-noir thriller film "Someone to Watch Over Me."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mike Keegan
Target entity description: Mike Keegan is the New York City police detective protagonist of the 1987 neo-noir thriller film "Someone to Watch Over Me."
  • A. Joe Kerrigan
    Joe Kerrigan is a former Major League Baseball pitching coach and brief Boston Red Sox manager best known for his long coaching career with several MLB teams.
  • B. Tom Keogh
    Tom Keogh was a noted costume designer best known for his work in mid-20th-century theatre and film productions.
  • C. Mick Burke
    Mick Burke was a renowned British mountaineer best known for his high-altitude climbs in the Himalayas and his work as a climbing cameraman on major expeditions.
  • D. Joe Keenan
    Joe Keenan is an American television writer, producer, and novelist best known for his work on the sitcom "Frasier" and other acclaimed comedy projects.
  • E. Kevin Duggan
    Kevin Duggan is a relatively obscure individual whose name is shared with multiple people across different professions, such as sports and public service.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf36c6b08190ba99400600e0b662 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cce10c88190bf25404fc4c75bbf completed May 8, 2026, 4:18 p.m.
NEDg Description generation batch_69fe1903c0f88190b6f1a081047506d5 completed May 8, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_69fe1980179481908b9f97e2f474e00d completed May 8, 2026, 5:12 p.m.
Created at: April 9, 2026, 9:42 p.m.