Triple

T15625308
Position Surface form Disambiguated ID Type / Status
Subject Safety Not Guaranteed E375662 entity
Predicate producer P490 FINISHED
Object Derek Connolly E269776 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: Derek Connolly | Statement: [Safety Not Guaranteed, producer, Derek Connolly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Derek Connolly
Context triple: [Safety Not Guaranteed, producer, Derek Connolly]
  • A. Derek Connolly chosen
    Derek Connolly is an American screenwriter best known for co-writing major science fiction and adventure films such as Jurassic World and its sequels.
  • B. Ryan Connolly
    Ryan Connolly is a filmmaker and YouTube personality best known for creating the popular filmmaking education channel Film Riot.
  • C. Derek Corrigan
    Derek Corrigan is a Canadian politician who served for many years as the mayor of Burnaby, British Columbia, known for his strong stances on urban development and environmental issues.
  • D. Ken Connell
    Ken Connell is a Marvel Comics character who becomes the human wielder of the immensely powerful cosmic artifact known as the Star Brand.
  • E. Chris Connolly
    Chris Connolly is a personal name shared by multiple individuals, including professionals in fields such as sports, media, and the arts.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e9e5e248190ae54cda1fde51efb completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff75655c948190aa1afa424e5270d1 completed May 9, 2026, 5:56 p.m.
Created at: April 10, 2026, 4:14 a.m.