Triple

T6028942
Position Surface form Disambiguated ID Type / Status
Subject Jason Isaacs E134250 entity
Predicate spouse P13 FINISHED
Object Emma Hewitt E328161 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: Emma Hewitt | Statement: [Jason Isaacs, spouse, Emma Hewitt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Hewitt
Context triple: [Jason Isaacs, spouse, Emma Hewitt]
  • A. Lara McDonnell
    Lara McDonnell is an Irish actress known for her roles in films such as "Belfast" (2021) and "Artemis Fowl."
  • B. Katie Blackburn
    Katie Blackburn is an American football executive who serves as the executive vice president of the Cincinnati Bengals and is one of the most prominent female leaders in the NFL.
  • C. Caroline Farrell
    Caroline Farrell is the original identity of Echo, the central protagonist in Joss Whedon’s science fiction TV series "Dollhouse."
  • D. Sophie Winkleman chosen
    Sophie Winkleman is a British actress known for roles in television series such as "Peep Show" and "Two and a Half Men," and is also a member of the extended British royal family.
  • E. Sarah Rowsell
    Sarah Rowsell was the wife of prominent 19th-century English architect Sir Charles Barry, known for supporting him throughout his career designing landmarks such as the Palace of Westminster.
  • 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_69c0087515148190a97475d412563865 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0560fdc84819093abba13054ea1ee completed March 22, 2026, 8:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1356aa44c8190aa2602bf77c00d2f completed March 23, 2026, 12:43 p.m.
Created at: March 22, 2026, 4:07 p.m.