Triple

T15026163
Position Surface form Disambiguated ID Type / Status
Subject Sarah Levy E378219 entity
Predicate spouse P13 FINISHED
Object Graham Outerbridge
Graham Outerbridge is an actor and producer known for his work in film and television and for being married to Canadian actress Sarah Levy.
E1199668 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: Graham Outerbridge | Statement: [Sarah Levy, spouse, Graham Outerbridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham Outerbridge
Context triple: [Sarah Levy, spouse, Graham Outerbridge]
  • A. George Oatley
    George Oatley was a British architect best known for designing prominent early 20th-century buildings in Bristol, England.
  • B. Frank Bannister
    Frank Bannister is a psychic investigator and con artist who can see and communicate with ghosts in the horror-comedy film "The Frighteners."
  • C. James Eccles
    James Eccles was a 19th-century British mountaineer noted for pioneering ascents in the Mont Blanc massif and other Alpine regions.
  • D. Stanley Argyle
    Stanley Argyle was an Australian politician who served as the Premier of Victoria in the early 1930s.
  • E. John Bainbridge
    John Bainbridge was a 17th-century English astronomer and physician noted for his early telescopic observations and influential astronomical writings.
  • 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: Graham Outerbridge
Triple: [Sarah Levy, spouse, Graham Outerbridge]
Generated description
Graham Outerbridge is an actor and producer known for his work in film and television and for being married to Canadian actress Sarah Levy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Graham Outerbridge
Target entity description: Graham Outerbridge is an actor and producer known for his work in film and television and for being married to Canadian actress Sarah Levy.
  • A. George Oatley
    George Oatley was a British architect best known for designing prominent early 20th-century buildings in Bristol, England.
  • B. Frank Bannister
    Frank Bannister is a psychic investigator and con artist who can see and communicate with ghosts in the horror-comedy film "The Frighteners."
  • C. James Eccles
    James Eccles was a 19th-century British mountaineer noted for pioneering ascents in the Mont Blanc massif and other Alpine regions.
  • D. Stanley Argyle
    Stanley Argyle was an Australian politician who served as the Premier of Victoria in the early 1930s.
  • E. John Bainbridge
    John Bainbridge was a 17th-century English astronomer and physician noted for his early telescopic observations and influential astronomical writings.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7dfcb508190aec8cd667e27a8ea completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffee31b70819092d0583100a7101a completed May 10, 2026, 3:43 a.m.
NEDg Description generation batch_6a00029e85388190bccc4a1996e1738e completed May 10, 2026, 3:59 a.m.
NED2 Entity disambiguation (via description) batch_6a0003031a4c8190887000d0179e07e5 completed May 10, 2026, 4:01 a.m.
Created at: April 10, 2026, 2:58 a.m.