Triple

T17069561
Position Surface form Disambiguated ID Type / Status
Subject The Loved Ones E414177 entity
Predicate director P255 FINISHED
Object Sean Byrne
Sean Byrne is an Australian filmmaker best known for directing the cult horror films "The Loved Ones" and "The Devil’s Candy."
E1250162 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: Sean Byrne | Statement: [The Loved Ones, director, Sean Byrne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sean Byrne
Context triple: [The Loved Ones, director, Sean Byrne]
  • A. Michael Byrne
    Michael Byrne is a British character actor known for his numerous film and television roles, often portraying military officers or authority figures.
  • B. Michael Treanor
    Michael Treanor is an American former child actor best known for playing Rocky, the eldest brother, in the early 1990s Three Ninjas film series.
  • C. Brian Byrne
    Brian Byrne is an Irish composer best known for his film scores and orchestral works, including the acclaimed music for the film "Albert Nobbs."
  • D. Brendan Vaughan
    Brendan Vaughan is an American media executive and journalist best known as the editor-in-chief of the business and innovation magazine Fast Company.
  • E. Dan Kavanagh
    Dan Kavanagh is the crime-fiction pseudonym used by British novelist Julian Barnes for a series of detective novels.
  • 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: Sean Byrne
Triple: [The Loved Ones, director, Sean Byrne]
Generated description
Sean Byrne is an Australian filmmaker best known for directing the cult horror films "The Loved Ones" and "The Devil’s Candy."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sean Byrne
Target entity description: Sean Byrne is an Australian filmmaker best known for directing the cult horror films "The Loved Ones" and "The Devil’s Candy."
  • A. Michael Byrne
    Michael Byrne is a British character actor known for his numerous film and television roles, often portraying military officers or authority figures.
  • B. Michael Treanor
    Michael Treanor is an American former child actor best known for playing Rocky, the eldest brother, in the early 1990s Three Ninjas film series.
  • C. Brian Byrne
    Brian Byrne is an Irish composer best known for his film scores and orchestral works, including the acclaimed music for the film "Albert Nobbs."
  • D. Brendan Vaughan
    Brendan Vaughan is an American media executive and journalist best known as the editor-in-chief of the business and innovation magazine Fast Company.
  • E. Dan Kavanagh
    Dan Kavanagh is the crime-fiction pseudonym used by British novelist Julian Barnes for a series of detective novels.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbbfb1f08190807301ff6e573cf5 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012eda04d08190b450fbfc6ccb9054 completed May 11, 2026, 1:20 a.m.
NEDg Description generation batch_6a01306334088190b6199b9bdd728c3c completed May 11, 2026, 1:26 a.m.
NED2 Entity disambiguation (via description) batch_6a01343b21508190bd8dc59765ec7f78 completed May 11, 2026, 1:43 a.m.
Created at: April 10, 2026, 5:34 a.m.