Triple

T21528769
Position Surface form Disambiguated ID Type / Status
Subject Freddie Thorp E531173 entity
Predicate notableWork P4 FINISHED
Object Safe NE NERFINISHED

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: Safe | Statement: [Freddie Thorp, notableWork, Safe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Safe
Context triple: [Freddie Thorp, notableWork, Safe]
  • A. Safe
    Safe is a 1995 psychological drama film directed by Todd Haynes, in which Julianne Moore plays a suburban housewife who develops a mysterious environmental illness, exploring themes of alienation, illness, and societal anxiety.
  • B. Safe chosen
    Safe is a 2012 action thriller film starring Jason Statham as a former elite agent who protects a young girl with a memorized code sought by the Triads, the Russian mob, and corrupt officials.
  • C. Safe
    "Safe" is a powerful short play by Georgia Douglas Johnson that confronts the horrors of racial violence and the emotional turmoil of Black motherhood in early 20th-century America.
  • D. SAFE
    SAFE (Saving Animals From Extinction) is a conservation initiative dedicated to protecting and recovering endangered animal species and their habitats.
  • E. SAFE
    SAFE is a World Customs Organization framework that sets global standards to enhance the security and efficiency of international trade and supply chains.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee8852e68c8190a5341c9f75081382 completed April 26, 2026, 9:49 p.m.
Created at: April 16, 2026, 6:27 p.m.