Triple

T10245875
Position Surface form Disambiguated ID Type / Status
Subject Austin Powers E240210 entity
Predicate ally P4662 FINISHED
Object Vanessa Kensington E446106 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: Vanessa Kensington | Statement: [Austin Powers, ally, Vanessa Kensington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vanessa Kensington
Context triple: [Austin Powers, ally, Vanessa Kensington]
  • A. Vanessa Kensington chosen
    Vanessa Kensington is a British intelligence agent and love interest in the Austin Powers film series, portrayed by Elizabeth Hurley.
  • B. Mel Hinds
    Mel Hinds is a child of American R&B and soul singer-songwriter Macy Gray.
  • C. Aoife Hinds
    Aoife Hinds is an Irish-British actress known for roles in film and television series such as "Normal People," "Derry Girls," and "The Lovers."
  • D. Cristina Vee
    Cristina Vee is an American voice actress known for her work in anime, video games, and animation, including prominent roles in series like "Miraculous Ladybug" and "Sailor Moon."
  • E. Vanessa Ives
    Vanessa Ives is a powerful, tormented medium and the central heroine of the horror drama series "Penny Dreadful," known for her complex struggle with supernatural forces and inner darkness.
  • 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_69d381a7e198819090280d5ab885d59e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d22cfe1c8190afae178e11a59b8b completed April 7, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f7a597188190880200d13784f18f completed April 9, 2026, 12:49 a.m.
Created at: April 6, 2026, 11:26 a.m.