Triple

T20006957
Position Surface form Disambiguated ID Type / Status
Subject Zen E494483 entity
Predicate castMember P1668 FINISHED
Object Peter Guinness NE NERFINISHED

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 Guinness | Statement: [Zen, castMember, Peter Guinness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Guinness
Context triple: [Zen, castMember, Peter Guinness]
  • A. Peter Guinness chosen
    Peter Guinness is a British actor known for his extensive work in film, television, and theatre, including a role in the 2013 TV miniseries "The Bible."
  • B. Geoffrey Hallowes
    Geoffrey Hallowes was a British intelligence officer and veteran of the Special Operations Executive during World War II, later known for his postwar work in the wine trade and his marriage to fellow SOE agent Odette Sansom.
  • C. Guy Vernon Henry
    Guy Vernon Henry was a 19th-century United States Army officer and Civil War veteran who later became a brigadier general and military governor in Puerto Rico during the Spanish–American War era.
  • D. Roy Goode
    Roy Goode is the fugitive outlaw protagonist of the Western miniseries "Godless," known for seeking redemption while being hunted by his former gang.
  • E. Harry Goode
    Harry Goode was a pioneering computer scientist and engineer recognized for his influential contributions to the early development of information processing and systems engineering.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a648a88190853ee741edcf6ca2 completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:33 p.m.