Triple

T21898379
Position Surface form Disambiguated ID Type / Status
Subject The Innkeepers E540742 entity
Predicate producer P490 FINISHED
Object Peter Phok 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: Peter Phok | Statement: [The Innkeepers, producer, Peter Phok]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Phok
Context triple: [The Innkeepers, producer, Peter Phok]
  • A. Peter Phok chosen
    Peter Phok is an American film producer known for his work on independent horror and genre films.
  • B. Peter Mathuki
    Peter Mathuki is a Kenyan diplomat and regional integration expert who serves as the Secretary General of the East African Community, overseeing the bloc’s policies and coordination among member states.
  • C. Terry Pheto
    Terry Pheto is a South African actress best known internationally for her roles in films such as "Tsotsi" and "Mandela: Long Walk to Freedom."
  • D. Tony Kgoroge
    Tony Kgoroge is a South African actor known for his roles in prominent films and television series, particularly those depicting South African history and social issues.
  • E. Phil Gubala
    Phil Gubala is a notable resident associated with the community of Affton, Missouri.
  • 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_69e0c47b4e8c81908c8076eaa4c8e4f2 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc8c2108190b55ff1ba3badc9fb completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:07 p.m.