Triple

T23298339
Position Surface form Disambiguated ID Type / Status
Subject Feast (2014 film) E590232 entity
Predicate storyBy P1955 FINISHED
Object Patrick Osborne 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: Patrick Osborne | Statement: [Feast (2014 film), storyBy, Patrick Osborne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patrick Osborne
Context triple: [Feast (2014 film), storyBy, Patrick Osborne]
  • A. Patrick Osborne chosen
    Patrick Osborne is an American animator and film director best known for his Academy Award-winning work on the Disney animated short film "Feast."
  • B. Patrick Osbourne
    Patrick Osbourne is a character from the television series "Revenge," known for his complex romantic involvement with tech billionaire Nolan Ross.
  • C. Will Osborne
    Will Osborne is a notable individual recognized for achievements significant enough to distinguish him among others sharing the Osborne surname.
  • D. Gregory Burke
    Gregory Burke is a Scottish playwright and screenwriter best known for his acclaimed stage play "Black Watch" and his work on films such as "’71" and "Entebbe."
  • E. Andrew Toney
    Andrew Toney is a former NBA All-Star guard best known for his explosive scoring and clutch playoff performances with the Philadelphia 76ers in the early 1980s.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d083188190abaae77dd4cf2bae completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.