Triple

T11249294
Position Surface form Disambiguated ID Type / Status
Subject Fable Legends E266284 entity
Predicate developer P73 FINISHED
Object Lionhead Studios E200541 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: Lionhead Studios | Statement: [Fable Legends, developer, Lionhead Studios]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lionhead Studios
Context triple: [Fable Legends, developer, Lionhead Studios]
  • A. Lionhead Studios chosen
    Lionhead Studios was a British video game developer best known for creating the Fable series and for its innovative, often experimental game designs under founder Peter Molyneux.
  • B. Avalon Studios
    Avalon Studios is a prominent New Zealand film and television production facility known for its soundstages and post-production services.
  • C. Slightly Mad Studios
    Slightly Mad Studios is a British video game developer best known for its work on racing titles such as the Project CARS series and entries in the Need for Speed franchise.
  • D. Swordfish Studios
    Swordfish Studios was a British video game development company known for creating titles such as World Championship Rugby and 50 Cent: Blood on the Sand.
  • E. Platinum Studios
    Platinum Studios is an entertainment company known for developing and producing comic book–based properties for film, television, and other media.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e93212448190b46b3799b0bdfa0f completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b7b051988190abec04740df75c89 completed April 20, 2026, 5:20 a.m.
Created at: April 8, 2026, 9:31 p.m.