Triple

T23298541
Position Surface form Disambiguated ID Type / Status
Subject Victor Marswell E590237 entity
Predicate romanticInvolvementWith P7325 FINISHED
Object Eloise Kelly 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: Eloise Kelly | Statement: [Victor Marswell, romanticInvolvementWith, Eloise Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eloise Kelly
Context triple: [Victor Marswell, romanticInvolvementWith, Eloise Kelly]
  • A. Eloise Kelly chosen
    Eloise Kelly is a spirited American woman and romantic lead in the 1953 adventure film "Mogambo," portrayed by Ava Gardner.
  • B. Eloise Taylor
    Eloise Taylor was the wife of American film and stage actor Pat O’Brien.
  • C. Eloise Taylor
    Eloise Taylor is a British aristocrat and granddaughter of Prince Edward, Duke of Kent, placing her within the extended British royal family.
  • D. Eloise Anderson
    Eloise Anderson is the young biracial girl at the center of a custody battle in the 2014 drama film "Black or White."
  • E. Eloise Mumford
    Eloise Mumford is an American actress known for her supporting role as Kate Kavanagh in the Fifty Shades film series and for her work in both television and independent films.
  • 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.