Triple

T13687001
Position Surface form Disambiguated ID Type / Status
Subject Exam E328157 entity
Predicate director P255 FINISHED
Object Stuart Hazeldine
Stuart Hazeldine is a British screenwriter and film director best known for his psychological thriller "Exam" and his work in the science fiction and fantasy genres.
E1073540 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: Stuart Hazeldine | Statement: [Exam, director, Stuart Hazeldine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stuart Hazeldine
Context triple: [Exam, director, Stuart Hazeldine]
  • A. Stuart Davies
    Stuart Davies was a British aeronautical engineer best known for leading the design of the Avro Vulcan strategic bomber.
  • B. Richard Hiscott
    Richard Hiscott is an editor known for his work on the television series "Willow."
  • C. Michael Staines
    Michael Staines was an Irish revolutionary and politician who became the inaugural head of Ireland’s national police force, the Garda Síochána, during the early years of the Irish Free State.
  • D. Alastair Stewart
    Alastair Stewart is a British journalist and long-serving television news presenter best known for his work with ITN and ITV News.
  • E. Geoffrey Haslam
    Geoffrey Haslam is a record producer best known for his work on Bette Midler’s debut album "The Divine Miss M."
  • 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: Stuart Hazeldine
Triple: [Exam, director, Stuart Hazeldine]
Generated description
Stuart Hazeldine is a British screenwriter and film director best known for his psychological thriller "Exam" and his work in the science fiction and fantasy genres.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stuart Hazeldine
Target entity description: Stuart Hazeldine is a British screenwriter and film director best known for his psychological thriller "Exam" and his work in the science fiction and fantasy genres.
  • A. Stuart Davies
    Stuart Davies was a British aeronautical engineer best known for leading the design of the Avro Vulcan strategic bomber.
  • B. Richard Hiscott
    Richard Hiscott is an editor known for his work on the television series "Willow."
  • C. Michael Staines
    Michael Staines was an Irish revolutionary and politician who became the inaugural head of Ireland’s national police force, the Garda Síochána, during the early years of the Irish Free State.
  • D. Alastair Stewart
    Alastair Stewart is a British journalist and long-serving television news presenter best known for his work with ITN and ITV News.
  • E. Geoffrey Haslam
    Geoffrey Haslam is a record producer best known for his work on Bette Midler’s debut album "The Divine Miss M."
  • 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_69d8076ff62081908a7bd79889edd7a0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc670968881908e2b4fdf656c7285 completed April 12, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac7c8bbc81908c7aa15c6892be34 completed May 6, 2026, 9:02 p.m.
NEDg Description generation batch_69fbb00b50208190be68a22ae90ef113 completed May 6, 2026, 9:18 p.m.
NED2 Entity disambiguation (via description) batch_69fbb082c6988190ac679f09449c133d completed May 6, 2026, 9:20 p.m.
Created at: April 9, 2026, 9:53 p.m.