Triple

T14879405
Position Surface form Disambiguated ID Type / Status
Subject Poltergeist E349957 entity
Predicate screenwriter P2831 FINISHED
Object Mark Victor E349957 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: Mark Victor | Statement: [Poltergeist, screenwriter, Mark Victor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Victor
Context triple: [Poltergeist, screenwriter, Mark Victor]
  • A. Mark Victor chosen
    Mark Victor is a screenwriter best known for co-writing the classic 1982 horror film "Poltergeist."
  • B. Mark Arnold
    Mark Arnold is an American actor best known for his role in the 1985 teen comedy film "Teen Wolf."
  • C. Michael Hinn
    Michael Hinn was an American actor known for supporting roles in mid-20th-century films, including the 1957 crime drama "The Big Boodle."
  • D. Matthew Marks
    Matthew Marks is an influential American art dealer and gallerist known for representing prominent contemporary artists through his eponymous gallery.
  • E. Christian Colson
    Christian Colson is a British film producer best known for his Academy Award-winning work on "Slumdog Millionaire" and other acclaimed dramas.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e622388190b2bf91cd10b9821d completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b5670108190b41ef95dc318be60 completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 1:55 a.m.