Triple

T10382439
Position Surface form Disambiguated ID Type / Status
Subject Timothy Shelley E244673 entity
Predicate familyName P18 FINISHED
Object Shelley E168629 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: Shelley | Statement: [Timothy Shelley, familyName, Shelley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shelley
Context triple: [Timothy Shelley, familyName, Shelley]
  • A. Shelley chosen
    Shelley is the surname of Mary Shelley, the English novelist best known as the author of the Gothic classic "Frankenstein."
  • B. Shelley
    Shelley is a key supporting character in the psychological thriller film "Don't Worry Darling," portrayed as the elegant yet enigmatic wife of the community's leader.
  • C. Shelley
    Shelley is a small village in Suffolk, England, situated within the scenic Dedham Vale countryside.
  • D. Shelley
    Shelley is a feminine given name most famously borne by American actress Shelley Duvall, known for her distinctive roles in 1970s and 1980s films.
  • E. Percy Bysshe Shelley
    Percy Bysshe Shelley was a major English Romantic poet known for his radical political views, lyrical style, and works such as "Ozymandias" and "Prometheus Unbound."
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e992d8e08190aaa9a04925f52ccc completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7959b6c2c819085b606280024c0f9 completed April 9, 2026, 12:03 p.m.
Created at: April 6, 2026, 12:04 p.m.