Triple

T10845360
Position Surface form Disambiguated ID Type / Status
Subject In Her Skin E255995 entity
Predicate hasCastMember P2308 FINISHED
Object Tom O’Sullivan
Tom O’Sullivan is an Australian actor known for his work in film, television, and theatre.
 E895949 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: Tom O’Sullivan | Statement: [In Her Skin, hasCastMember, Tom O’Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom O’Sullivan
Context triple: [In Her Skin, hasCastMember, Tom O’Sullivan]
  • A. Jim O’Brien
    Jim O’Brien is the father of American actress Peri Gilpin, best known for her role as Roz Doyle on the television series "Frasier."
  • B. Jim O’Brien
    Jim O’Brien is a former American football placekicker best known for kicking the game-winning field goal for the Baltimore Colts in Super Bowl V.
  • C. Tom McLoughlin
    Tom McLoughlin is an American film and television director and screenwriter best known for his work in the horror genre, including directing "Friday the 13th Part VI: Jason Lives."
  • D. Michael O’Rourke
    Michael O’Rourke is an Irish media entrepreneur best known as a co-founder of the international sports television network Setanta Sports.
  • E. Peter O’Neill
    Peter O’Neill is a Papua New Guinean politician who served as Prime Minister of Papua New Guinea from 2011 to 2019.
  • 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: Tom O’Sullivan
Triple: [In Her Skin, hasCastMember, Tom O’Sullivan]
Generated description
Tom O’Sullivan is an Australian actor known for his work in film, television, and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom O’Sullivan
Target entity description: Tom O’Sullivan is an Australian actor known for his work in film, television, and theatre.
  • A. Jim O’Brien
    Jim O’Brien is the father of American actress Peri Gilpin, best known for her role as Roz Doyle on the television series "Frasier."
  • B. Jim O’Brien
    Jim O’Brien is a former American football placekicker best known for kicking the game-winning field goal for the Baltimore Colts in Super Bowl V.
  • C. Tom McLoughlin
    Tom McLoughlin is an American film and television director and screenwriter best known for his work in the horror genre, including directing "Friday the 13th Part VI: Jason Lives."
  • D. Michael O’Rourke
    Michael O’Rourke is an Irish media entrepreneur best known as a co-founder of the international sports television network Setanta Sports.
  • E. Peter O’Neill
    Peter O’Neill is a Papua New Guinean politician who served as Prime Minister of Papua New Guinea from 2011 to 2019.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d750d0155c81908fb55ba6b45db800 completed April 9, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23b7578688190975c087d28808be5 completed April 17, 2026, 1:53 p.m.
NEDg Description generation batch_69e2453f6f008190847298f4006290f7 completed April 17, 2026, 2:35 p.m.
NED2 Entity disambiguation (via description) batch_69e288b1d64c8190b31313634b706d0a completed April 17, 2026, 7:23 p.m.
Created at: April 8, 2026, 9:19 p.m.