Triple

T14065889
Position Surface form Disambiguated ID Type / Status
Subject Rebecca Randall E338469 entity
Predicate guardian P28704 FINISHED
Object Miranda Sawyer E749552 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: Miranda Sawyer | Statement: [Rebecca Randall, guardian, Miranda Sawyer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miranda Sawyer
Context triple: [Rebecca Randall, guardian, Miranda Sawyer]
  • A. Miranda Sawyer chosen
    Miranda Sawyer is a British journalist, broadcaster, and arts critic known for her work in music and culture writing, particularly for The Observer and on BBC radio.
  • B. Miranda Cooper
    Miranda Cooper is a British songwriter and producer best known for crafting numerous pop hits, particularly for acts like Girls Aloud and Sugababes.
  • C. Miranda Jones
    Miranda Jones is a human telepath and psychologist featured in the original Star Trek series episode "Is There in Truth No Beauty?".
  • D. Miranda Greene
    Miranda Greene is a fictional character from the comedy film "King Ralph," where she serves as a key romantic interest and supporting figure in the story of an unlikely American who becomes the King of England.
  • E. Miranda Green
    Miranda Green is a British journalist and political commentator known for her analysis and appearances across UK broadcast media.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de568b81f08190a571004261c0e8e4 completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb669111081909ccd167f41571a00 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:21 p.m.