Triple

T9980351
Position Surface form Disambiguated ID Type / Status
Subject Full Throttle E196434 entity
Predicate author P4 FINISHED
Object Joe Hill E37484 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: Joe Hill | Statement: [Full Throttle, author, Joe Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Hill
Context triple: [Full Throttle, author, Joe Hill]
  • A. Joe Hill chosen
    Joe Hill is an American author known for his horror and dark fantasy novels and comics, and is the son of writer Stephen King.
  • B. Mark Frost
    Mark Frost is an American novelist, screenwriter, and producer best known as the co-creator of the television series "Twin Peaks."
  • C. Will Bruder
    Will Bruder is an American architect known for his innovative, materially expressive designs and significant cultural projects throughout the American Southwest.
  • D. John Saul
    John Saul was a male prostitute in late 19th-century London whose involvement in the 1889 Cleveland Street scandal linked him to a high-profile case of homosexual activity and social controversy in Victorian Britain.
  • E. Max Allan Collins
    Max Allan Collins is an American mystery and crime writer best known for his graphic novel "Road to Perdition" and his extensive work in detective fiction and tie-in novels.
  • 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_69ca82efbce081908179b4b9c65096eb completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb8b9aca881908a9b5dfd7e0de4ba completed April 2, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d257df420881909edac01b4e331c1e completed April 5, 2026, 12:38 p.m.
Created at: March 30, 2026, 8:49 p.m.