Triple

T22755991
Position Surface form Disambiguated ID Type / Status
Subject Gracie Hart E562843 entity
Predicate creator P184 FINISHED
Object Katie Ford E1332873 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: Katie Ford | Statement: [Gracie Hart, creator, Katie Ford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katie Ford
Context triple: [Gracie Hart, creator, Katie Ford]
  • A. Katie Ford chosen
    Katie Ford is a Canadian-American screenwriter best known for co-writing the hit comedy film "Miss Congeniality" and for her work in television.
  • B. Katie Featherston
    Katie Featherston is an American actress best known for her role as Katie in the "Paranormal Activity" horror film series.
  • C. Katie Carpenter
    Katie Carpenter is a television producer best known for her executive production work on the medical dramedy series "This Is Going to Hurt."
  • D. Katie Findlay
    Katie Findlay is a Canadian actress best known for her roles in television series such as "The Killing," "How to Get Away with Murder," and "The Carrie Diaries."
  • E. Katie Lyons
    Katie Lyons is a British actress known for her comedic roles in television series such as Green Wing and other UK comedies.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179bd22588190ac724a656194f5b9 completed April 29, 2026, 3:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf28f11c481908d5e464f31aeada3 completed May 19, 2026, 5:18 a.m.
Created at: April 17, 2026, 3:25 p.m.