Triple

T5705968
Position Surface form Disambiguated ID Type / Status
Subject I Am Legend (film) E125784 entity
Predicate screenwriter P2831 FINISHED
Object Mark Protosevich E197176 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 Protosevich | Statement: [I Am Legend (film), screenwriter, Mark Protosevich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Protosevich
Context triple: [I Am Legend (film), screenwriter, Mark Protosevich]
  • A. Mark Protosevich chosen
    Mark Protosevich is an American screenwriter known for his work on major genre films such as "Thor" and "I Am Legend."
  • B. Kirill Shubsky
    Kirill Shubsky is a Russian businessman known primarily as the husband of actress and model Anastasia Shubskaya.
  • C. Nikita Anisimov
    Nikita Anisimov is a Russian academic and university administrator who serves as the rector of the National Research University Higher School of Economics (HSE) in Moscow.
  • D. Adam Bielecki
    Adam Bielecki is a Polish high-altitude mountaineer renowned for pioneering bold winter ascents in the Himalayas and Karakoram.
  • E. Tyler Matakevich
    Tyler Matakevich is an American football linebacker and special teams standout in the NFL, known for his prolific college career at Temple University and his later role with teams such as the Buffalo Bills.
  • 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_69c0082d6fe48190b777fb383769e5c8 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02459cd18819080fda0b481d11f08 completed March 22, 2026, 5:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a666d788190a0f786d12391a44b completed March 22, 2026, 9:08 p.m.
Created at: March 22, 2026, 3:45 p.m.