Triple

T11145044
Position Surface form Disambiguated ID Type / Status
Subject The Lovely Bones E263647 entity
Predicate character P662 FINISHED
Object Susie Salmon E850919 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: Susie Salmon | Statement: [The Lovely Bones, character, Susie Salmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susie Salmon
Context triple: [The Lovely Bones, character, Susie Salmon]
  • A. Susie Salmon chosen
    Susie Salmon is the murdered teenage narrator of Alice Sebold’s novel and its 2009 film adaptation The Lovely Bones, who observes her family and killer from the afterlife.
  • B. Susie Brown
    Susie Brown is a fictional character portrayed by Viola Davis, likely serving as a significant supporting figure in the story she appears in.
  • C. Susie
    Susie is a recurring character from the animated television series "Family Guy," known as the infant daughter of Joe and Bonnie Swanson.
  • D. Sissy Sullivan
    Sissy Sullivan is a supporting character in the film "Shame," contributing to the emotional and psychological depth of the story.
  • E. Sally Hibbin
    Sally Hibbin is a British film and television producer known for her collaborations with director Ken Loach and her work on socially conscious, independent films.
  • 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_69d6aa9c0ba08190bbd19c217489b755 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8634d5481909b114d30a542ea3f completed April 9, 2026, 5:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69e496c152a081909c6ad8b2a6e41927 completed April 19, 2026, 8:48 a.m.
Created at: April 8, 2026, 9:28 p.m.