Triple

T20739112
Position Surface form Disambiguated ID Type / Status
Subject J. Willard Marriott E509790 entity
Predicate spouse P13 FINISHED
Object Alice Sheets Marriott 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: Alice Sheets Marriott | Statement: [J. Willard Marriott, spouse, Alice Sheets Marriott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alice Sheets Marriott
Context triple: [J. Willard Marriott, spouse, Alice Sheets Marriott]
  • A. Alice Marriott chosen
    Alice Marriott was an American businesswoman and co-founder of the global hospitality company Marriott International.
  • B. Sylvia Marriott
    Sylvia Marriott was a British actress known for her supporting roles in mid-20th-century film and television productions.
  • C. Yvonne Catherine Hilton
    Yvonne Catherine Hilton is best known as the wife of British writer and musician Neil Innes, a key figure in comedy and parody rock.
  • D. Liz Whitney
    Liz Whitney was an American socialite and prominent racehorse owner and breeder who became well known through her marriage into the wealthy Whitney family.
  • E. Jennifer Hilton
    Jennifer Hilton is a film producer known for her work on the movie "The First Time."
  • 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_69e0b4c589c08190834fb5d86d0efa2b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c20d9d4c8190a2fd87f8a33c313d completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:32 p.m.