Triple

T2350535
Position Surface form Disambiguated ID Type / Status
Subject Insomnia (2002 film) E47436 entity
Predicate character P662 FINISHED
Object Will Dormer
Will Dormer is a seasoned but morally conflicted Los Angeles detective whose insomnia and guilt intensify as he investigates a murder in a small Alaskan town in the film "Insomnia."
 E258360 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: Will Dormer | Statement: [Insomnia (2002 film), character, Will Dormer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Will Dormer
Context triple: [Insomnia (2002 film), character, Will Dormer]
  • A. John Dawson
    John Dawson was a pioneering American plasma physicist renowned for his foundational contributions to plasma theory and fusion research.
  • B. John Dawson
    John Dawson is a fictional character named John Dawson who appears in the work featuring the character Dawn.
  • C. Donald Wolfit
    Donald Wolfit was a renowned English stage and film actor, particularly celebrated for his Shakespearean performances and his powerful, often larger-than-life acting style.
  • D. Sean Mortimer
    Sean Mortimer is a music video director known for his work with the artist Juicy.
  • E. Ben Dreith
    Ben Dreith is a former American football official best known for his long career as an NFL referee, including working high-profile games such as Super Bowl XV.
  • 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: Will Dormer
Triple: [Insomnia (2002 film), character, Will Dormer]
Generated description
Will Dormer is a seasoned but morally conflicted Los Angeles detective whose insomnia and guilt intensify as he investigates a murder in a small Alaskan town in the film "Insomnia."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Will Dormer
Target entity description: Will Dormer is a seasoned but morally conflicted Los Angeles detective whose insomnia and guilt intensify as he investigates a murder in a small Alaskan town in the film "Insomnia."
  • A. John Dawson
    John Dawson was a pioneering American plasma physicist renowned for his foundational contributions to plasma theory and fusion research.
  • B. John Dawson
    John Dawson is a fictional character named John Dawson who appears in the work featuring the character Dawn.
  • C. Donald Wolfit
    Donald Wolfit was a renowned English stage and film actor, particularly celebrated for his Shakespearean performances and his powerful, often larger-than-life acting style.
  • D. Sean Mortimer
    Sean Mortimer is a music video director known for his work with the artist Juicy.
  • E. Ben Dreith
    Ben Dreith is a former American football official best known for his long career as an NFL referee, including working high-profile games such as Super Bowl XV.
  • 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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc6cfffc88190b49433f52581420e completed March 7, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae962f769881909a7713880eaa9b84 completed March 9, 2026, 9:43 a.m.
NEDg Description generation batch_69ae96b399608190bfa846c433612142 completed March 9, 2026, 9:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae977aac9c8190b5fecd5fea8893fd completed March 9, 2026, 9:48 a.m.
Created at: March 4, 2026, 7:54 p.m.