Triple

T8481961
Position Surface form Disambiguated ID Type / Status
Subject Demis Hassabis E200539 entity
Predicate workedAt P7 FINISHED
Object Elixir Studios E200542 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: Elixir Studios | Statement: [Demis Hassabis, workedAt, Elixir Studios]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elixir Studios
Context triple: [Demis Hassabis, workedAt, Elixir Studios]
  • A. Elixir Studios chosen
    Elixir Studios was a British video game development company known for strategy and simulation titles in the early 2000s.
  • B. Oats Studios
    Oats Studios is an experimental film production company known for releasing innovative, high-concept sci-fi and horror short films, often distributed online.
  • C. Cryptic Studios
    Cryptic Studios is an American video game developer best known for creating online role-playing games such as City of Heroes, Champions Online, and Star Trek Online.
  • D. Cosmos Studios
    Cosmos Studios is a media production company founded by science communicator Ann Druyan that creates documentaries and content focused on science, space, and the legacy of Carl Sagan’s work.
  • E. Trilith Studios
    Trilith Studios is a major film and television production complex in Georgia known for hosting large-scale projects, including many Marvel Cinematic Universe movies.
  • 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_69ca831b17988190a1f3f3413d57b820 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe53638c48190b742fc51d1b4442a completed March 31, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a2b2e9081909f19712946c6ec20 completed April 2, 2026, 9:43 a.m.
Created at: March 30, 2026, 6:12 p.m.