Triple

T21687161
Position Surface form Disambiguated ID Type / Status
Subject Anna Faris E535258 entity
Predicate child P120 FINISHED
Object Jack Pratt 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: Jack Pratt | Statement: [Anna Faris, child, Jack Pratt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Pratt
Context triple: [Anna Faris, child, Jack Pratt]
  • A. Jack Pratt chosen
    Jack Pratt is the son of American actor Chris Pratt and actress Anna Faris.
  • B. Jack Pratt
    Jack Pratt is a relatively obscure or ambiguously identified individual for whom no widely recognized public profile or notable achievements are readily documented.
  • C. Greg Pratt
    Greg Pratt is a fictional emergency medicine physician and central character on the television series "ER," known for his strong-willed personality and evolving leadership in the hospital's ER.
  • D. Grahame Pratt
    Grahame Pratt is an Australian-born actor and producer best known as the longtime husband and manager of American singer and actress Leslie Uggams.
  • E. David Pratt
    David Pratt is known as the husband of Kyle Pratt.
  • 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_69e0c469b6ec8190aee4cadd1527db91 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef96cc31b8819086ca980521f94501 completed April 27, 2026, 5:03 p.m.
Created at: April 16, 2026, 6:44 p.m.