Triple

T10124433
Position Surface form Disambiguated ID Type / Status
Subject American Psycho E226175 entity
Predicate editedBy P1954 FINISHED
Object Andrew Marcus
Andrew Marcus is a film editor best known for his work on the psychological thriller "American Psycho."
E259338 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: Andrew Marcus | Statement: [American Psycho, editedBy, Andrew Marcus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Marcus
Context triple: [American Psycho, editedBy, Andrew Marcus]
  • A. Andrew Marcus
    Andrew Marcus is a literary editor known for preparing an edition of E. M. Forster’s novel "Howards End."
  • B. Andrew Marcus
    Andrew Marcus is a film editor best known for his work on major feature films, including Kenneth Branagh’s adaptation of "Much Ado About Nothing."
  • C. Adam Marcus
    Adam Marcus is an American filmmaker and screenwriter best known for directing "Jason Goes to Hell: The Final Friday" and co-writing the horror sequel "Texas Chainsaw 3D."
  • D. Ben Marcus
    Ben Marcus is an American author known for his experimental, linguistically inventive fiction and influential short story collections and novels.
  • E. Ian Murdock
    Ian Murdock was an American software engineer best known as the creator of the Debian GNU/Linux operating system.
  • 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: Andrew Marcus
Triple: [American Psycho, editedBy, Andrew Marcus]
Generated description
Andrew Marcus is a film editor best known for his work on the psychological thriller "American Psycho."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andrew Marcus
Target entity description: Andrew Marcus is a film editor best known for his work on the psychological thriller "American Psycho."
  • A. Andrew Marcus
    Andrew Marcus is a literary editor known for preparing an edition of E. M. Forster’s novel "Howards End."
  • B. Andrew Marcus chosen
    Andrew Marcus is a film editor best known for his work on major feature films, including Kenneth Branagh’s adaptation of "Much Ado About Nothing."
  • C. Adam Marcus
    Adam Marcus is an American filmmaker and screenwriter best known for directing "Jason Goes to Hell: The Final Friday" and co-writing the horror sequel "Texas Chainsaw 3D."
  • D. Ben Marcus
    Ben Marcus is an American author known for his experimental, linguistically inventive fiction and influential short story collections and novels.
  • E. Ian Murdock
    Ian Murdock was an American software engineer best known as the creator of the Debian GNU/Linux operating system.
  • F. None of above.

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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd2ebe4548190a484c145639d92f0 completed April 2, 2026, 2:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc5cb62081908f4725de14916c11 completed April 5, 2026, 8:55 p.m.
NEDg Description generation batch_69d2cd901c148190afb27759cc176f89 completed April 5, 2026, 9:01 p.m.
NED2 Entity disambiguation (via description) batch_69d2ce71fa888190b8dd13df83a2cd78 completed April 5, 2026, 9:04 p.m.
Created at: March 30, 2026, 9:05 p.m.