Triple

T9449852
Position Surface form Disambiguated ID Type / Status
Subject Charlotte Rampling E227858 entity
Predicate spouse P13 FINISHED
Object Bryan Southcombe
Bryan Southcombe is a New Zealand-born actor and publicist best known for his former marriage to British actress Charlotte Rampling.
E814444 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: Bryan Southcombe | Statement: [Charlotte Rampling, spouse, Bryan Southcombe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bryan Southcombe
Context triple: [Charlotte Rampling, spouse, Bryan Southcombe]
  • A. Doug Bowne
    Doug Bowne is a musician best known for his work with the new wave band Tom Tom Club.
  • B. Bryan Bedford
    Bryan Bedford is an American airline executive best known for leading regional carriers such as Chautauqua Airlines and Republic Airways Holdings.
  • C. Bryan Bedford
    Bryan Bedford is the young boy central to the 1994 film "Miracle on 34th Street," whose belief in Santa Claus becomes a key focus of the story.
  • D. Brian Souter
    Brian Souter is a Scottish businessman best known as the co-founder of the Stagecoach Group and a prominent figure in the UK transport industry.
  • E. Geoff Pierson
    Geoff Pierson is an American actor known for his work in television dramas and comedies, including prominent roles on shows like Dexter and Unhappily Ever After.
  • 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: Bryan Southcombe
Triple: [Charlotte Rampling, spouse, Bryan Southcombe]
Generated description
Bryan Southcombe is a New Zealand-born actor and publicist best known for his former marriage to British actress Charlotte Rampling.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bryan Southcombe
Target entity description: Bryan Southcombe is a New Zealand-born actor and publicist best known for his former marriage to British actress Charlotte Rampling.
  • A. Doug Bowne
    Doug Bowne is a musician best known for his work with the new wave band Tom Tom Club.
  • B. Bryan Bedford
    Bryan Bedford is an American airline executive best known for leading regional carriers such as Chautauqua Airlines and Republic Airways Holdings.
  • C. Bryan Bedford
    Bryan Bedford is the young boy central to the 1994 film "Miracle on 34th Street," whose belief in Santa Claus becomes a key focus of the story.
  • D. Brian Souter
    Brian Souter is a Scottish businessman best known as the co-founder of the Stagecoach Group and a prominent figure in the UK transport industry.
  • E. Geoff Pierson
    Geoff Pierson is an American actor known for his work in television dramas and comedies, including prominent roles on shows like Dexter and Unhappily Ever After.
  • 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_69ca8439f8bc8190997f2ef40c9f0bc2 completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f6649a48190b6844daa6202efe5 completed April 1, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d190cc06d48190b437edfc4fee8cce completed April 4, 2026, 10:29 p.m.
NEDg Description generation batch_69d192f37e54819099d316ce44de2c81 completed April 4, 2026, 10:38 p.m.
NED2 Entity disambiguation (via description) batch_69d1933ffc3481909395c9efb63875bb completed April 4, 2026, 10:40 p.m.
Created at: March 30, 2026, 7:51 p.m.