Triple

T12532209
Position Surface form Disambiguated ID Type / Status
Subject Fell E299596 entity
Predicate hasNotableBearer P458 FINISHED
Object Robert Fell
Robert Fell was a 17th-century English academic who served as Dean of Christ Church, Oxford, and Vice-Chancellor of the University of Oxford.
 E988664 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: Robert Fell | Statement: [Fell, hasNotableBearer, Robert Fell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Robert Fell
Context triple: [Fell, hasNotableBearer, Robert Fell]
  • A. Robert Fellows
    Robert Fellows was an American film producer active during Hollywood's mid-20th century studio era, known for his work on numerous genre and adventure films.
  • B. Robert Fry
    Robert Fry is a British artist and former Royal Marines officer known for his contemporary figurative paintings and military service.
  • C. Edward Douglas Fawcett
    Edward Douglas Fawcett was a British philosopher, novelist, and mountaineer known for his works on idealist philosophy and speculative fiction.
  • D. Charles Fergusson
    Charles Fergusson was a senior British Army officer and general who played a prominent command role on the Western Front during World War I.
  • E. James Fawcett
    James Fawcett was an architect best known for co-designing Melbourne’s iconic Flinders Street Station.
  • 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: Robert Fell
Triple: [Fell, hasNotableBearer, Robert Fell]
Generated description
Robert Fell was a 17th-century English academic who served as Dean of Christ Church, Oxford, and Vice-Chancellor of the University of Oxford.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Robert Fell
Target entity description: Robert Fell was a 17th-century English academic who served as Dean of Christ Church, Oxford, and Vice-Chancellor of the University of Oxford.
  • A. Robert Fellows
    Robert Fellows was an American film producer active during Hollywood's mid-20th century studio era, known for his work on numerous genre and adventure films.
  • B. Robert Fry
    Robert Fry is a British artist and former Royal Marines officer known for his contemporary figurative paintings and military service.
  • C. Edward Douglas Fawcett
    Edward Douglas Fawcett was a British philosopher, novelist, and mountaineer known for his works on idealist philosophy and speculative fiction.
  • D. Charles Fergusson
    Charles Fergusson was a senior British Army officer and general who played a prominent command role on the Western Front during World War I.
  • E. James Fawcett
    James Fawcett was an architect best known for co-designing Melbourne’s iconic Flinders Street Station.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546b8fd48190ae90e80785b2e2d1 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65577e3388190b6c1c2e8dee7f6ac completed May 2, 2026, 7:50 p.m.
NEDg Description generation batch_69f6566e7bf88190a33c609caf9b4f3d completed May 2, 2026, 7:54 p.m.
NED2 Entity disambiguation (via description) batch_69f657aec8fc8190b3b08ccb95595958 completed May 2, 2026, 7:59 p.m.
Created at: April 8, 2026, 9:57 p.m.