Triple

T10845210
Position Surface form Disambiguated ID Type / Status
Subject Rake E255991 entity
Predicate executiveProducer P7225 FINISHED
Object Peter Duncan E899920 NE FINISHED

How this triple was built (2 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: Peter Duncan | Statement: [Rake, executiveProducer, Peter Duncan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Duncan
Context triple: [Rake, executiveProducer, Peter Duncan]
  • A. Peter Duncan chosen
    Peter Duncan is a British television presenter and former Blue Peter host who later became known for his adventurous travel documentaries and family-focused programming.
  • B. Ian Duncan
    Ian Duncan is a neurotic and often ineffectual psychology professor on the sitcom "Community," portrayed by comedian John Oliver.
  • C. Andrew Duncan
    Andrew Duncan was a British industrialist and politician who served as the United Kingdom’s Minister of Supply during the Second World War.
  • D. Arthur Duncan
    Arthur Duncan was an American tap dancer and entertainer best known for his groundbreaking television appearances, including as a featured performer on The Lawrence Welk Show.
  • E. Duncan Chalk
    Duncan Chalk is a powerful, manipulative media magnate in Robert Silverberg’s science fiction novel "Thorns," known for exploiting others’ pain for entertainment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69e3a91a3e1c819083ef144e7fd5603f completed April 18, 2026, 3:54 p.m.
Created at: April 8, 2026, 9:19 p.m.