Triple

T20080696
Position Surface form Disambiguated ID Type / Status
Subject Snake Eyes E499990 entity
Predicate stars P1956 FINISHED
Object Andrew Koji 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: Andrew Koji | Statement: [Snake Eyes, stars, Andrew Koji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Koji
Context triple: [Snake Eyes, stars, Andrew Koji]
  • A. Andrew Koji chosen
    Andrew Koji is a British actor and martial artist best known for his lead role in the TV series "Warrior" and his appearance in the action-comedy film "Bullet Train."
  • B. Logan Marshall-Green
    Logan Marshall-Green is an American actor and director known for his roles in films like "Prometheus" and "Upgrade" as well as various television series.
  • C. Taron Johnson
    Taron Johnson is an American football cornerback in the NFL, known for his standout play with the Buffalo Bills after a successful college career at Weber State.
  • D. Jai Courtney
    Jai Courtney is an Australian actor known for his roles in action and blockbuster films such as the Divergent series, A Good Day to Die Hard, and Suicide Squad.
  • E. Nathan Walker
    Nathan Walker is an Australian professional ice hockey forward known for being the first Australian to play in the NHL.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66557c19c8190b511857490bbd423 completed April 20, 2026, 5:41 p.m.
Created at: April 11, 2026, 3:41 p.m.