Triple

T16229426
Position Surface form Disambiguated ID Type / Status
Subject iMurders E393939 entity
Predicate hasCastMember P2308 FINISHED
Object Tony Todd E1083522 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: Tony Todd | Statement: [iMurders, hasCastMember, Tony Todd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Todd
Context triple: [iMurders, hasCastMember, Tony Todd]
  • A. Tony Todd chosen
    Tony Todd is an American actor best known for his commanding presence in horror films, particularly his iconic role as the title character in the "Candyman" franchise.
  • B. Doug Bradley
    Doug Bradley is an English actor best known for playing the iconic horror character Pinhead in the Hellraiser film series.
  • C. Donald Pleasence
    Donald Pleasence was an English character actor renowned for his intense performances in film and television, including iconic roles in the "Halloween" series and "The Great Escape."
  • D. Lance Henriksen
    Lance Henriksen is an American character actor best known for his intense performances in science fiction and horror films such as the Alien franchise and the TV series Millennium.
  • E. Udo Kier
    Udo Kier is a German actor known for his distinctive, often eccentric performances in European art-house films and cult horror movies, as well as numerous international productions.
  • 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_69d87f204df88190a8f88923decf9835 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e23d2889688190ac04e4e9479cabf4 completed April 17, 2026, 2:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ed71f488190bcdc2dcc74e5c5d3 completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:03 a.m.