Triple

T14816571
Position Surface form Disambiguated ID Type / Status
Subject Zoe Tapper E348332 entity
Predicate notableWork P4 FINISHED
Object Safe House E724886 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: Safe House | Statement: [Zoe Tapper, notableWork, Safe House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Safe House
Context triple: [Zoe Tapper, notableWork, Safe House]
  • A. Safe House chosen
    Safe House is a British television drama series featuring Steven Mackintosh in a prominent role, centered on a former detective who turns his remote guest house into a police safe house.
  • B. Safe House
    Safe House is a 2012 action thriller film starring Denzel Washington and Ryan Reynolds, centered on a young CIA agent tasked with guarding a dangerous fugitive in a compromised safe house in South Africa.
  • C. Our House
    Our House is a satirical play by Theresa Rebeck that critiques the intersection of reality television, corporate media, and American culture.
  • D. Our House
    "Our House" is a 1982 hit single by British ska/pop band Madness, known for its catchy melody and nostalgic lyrics about family life.
  • E. Our House
    "Our House" is a film project associated with actress and filmmaker Nicola Peltz Beckham, reflecting her work behind the camera as well as on screen.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe2c1ec81908b3dff7a5d0e85d0 completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe3897691c819085ef89480e730723 completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:49 a.m.