Triple

T20076990
Position Surface form Disambiguated ID Type / Status
Subject My Sister's Keeper E499892 entity
Predicate stars P1956 FINISHED
Object Thomas Dekker 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: Thomas Dekker | Statement: [My Sister's Keeper, stars, Thomas Dekker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Dekker
Context triple: [My Sister's Keeper, stars, Thomas Dekker]
  • A. Thomas Dekker
    Thomas Dekker was an English Renaissance dramatist and pamphleteer best known for his lively city comedies and vivid depictions of London life.
  • B. Thomas Dekker chosen
    Thomas Dekker is an American actor best known for his roles in science fiction and horror projects, including playing John Connor in the TV series "Terminator: The Sarah Connor Chronicles."
  • C. Patrick Welman
    Patrick Welman is a Dutch politician who serves as the mayor of the municipality of Oldenzaal in the Netherlands.
  • D. Chris Riddell
    Chris Riddell is a British illustrator and political cartoonist renowned for his distinctive artwork in children's literature and fantasy novels.
  • E. Ty Franck
    Ty Franck is an American science fiction writer and television producer best known as one half of the James S. A. Corey duo behind The Expanse novel series and its TV adaptation.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6643d5238819098b7d4e4e2c8dd67 completed April 20, 2026, 5:37 p.m.
Created at: April 11, 2026, 3:40 p.m.