Triple

T8440718
Position Surface form Disambiguated ID Type / Status
Subject Clement Freud E199343 entity
Predicate child P120 FINISHED
Object Matthew Freud E335802 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: Matthew Freud | Statement: [Clement Freud, child, Matthew Freud]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Freud
Context triple: [Clement Freud, child, Matthew Freud]
  • A. Matthew Freud chosen
    Matthew Freud is a British public relations executive and founder of the London-based agency Freud Communications.
  • B. William Freind
    William Freind was an 18th-century English clergyman who served as Dean of Canterbury and was known for his connections to prominent ecclesiastical and academic figures of his time.
  • C. Oliver Freud
    Oliver Freud was the son of psychoanalyst Sigmund Freud and brother of Anna Freud, known primarily through his connection to the prominent Freud family.
  • D. Barrett Foa
    Barrett Foa is an American actor best known for his long-running role as tech specialist Eric Beale on the television series NCIS: Los Angeles.
  • E. Hugh Laing
    Hugh Laing was a prominent mid-20th-century ballet dancer and actor, best known for his work with choreographer Antony Tudor and performances with major ballet companies.
  • 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_69ca8314cd6c8190a6b8c2a1096e18f3 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe138a94081908e306d22aaa39b24 completed March 31, 2026, 2:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d9140b48190ad0c493948a3de5e completed April 2, 2026, 7:41 a.m.
Created at: March 30, 2026, 6:08 p.m.