Triple

T20383826
Position Surface form Disambiguated ID Type / Status
Subject Ship Ahoy E497907 entity
Predicate hasCastMember P2308 FINISHED
Object Virginia O'Brien 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: Virginia O'Brien | Statement: [Ship Ahoy, hasCastMember, Virginia O'Brien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Virginia O'Brien
Context triple: [Ship Ahoy, hasCastMember, Virginia O'Brien]
  • A. Virginia O'Brien chosen
    Virginia O'Brien was an American film actress and singer best known for her deadpan comedic style and musical performances in MGM musicals of the 1940s.
  • B. Grace O'Brien
    Grace O'Brien is a character in the television series "Doctor Who," known as the wise and compassionate grandmother of companion Ryan Sinclair.
  • C. Florence Dempsey
    Florence Dempsey is a spirited young reporter character in the 1933 horror film "Mystery of the Wax Museum," known for her sharp wit and investigative tenacity.
  • D. Karen O’Brien
    Karen O’Brien is a British academic and university leader who serves as Vice-Chancellor of Durham University, overseeing its strategic direction and academic mission.
  • E. Virginia O'Connor
    Virginia O'Connor was the wife of renowned American composer and conductor Henry Mancini.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.