Triple

T11087021
Position Surface form Disambiguated ID Type / Status
Subject Mad Mouse E262146 entity
Predicate designer P184 FINISHED
Object Arrow Dynamics E185277 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: Arrow Dynamics | Statement: [Mad Mouse, designer, Arrow Dynamics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arrow Dynamics
Context triple: [Mad Mouse, designer, Arrow Dynamics]
  • A. Arrow Development chosen
    Arrow Development was an American ride engineering and manufacturing company renowned for pioneering modern roller coasters and theme park attractions for clients like Disneyland.
  • B. Alias Systems Corporation
    Alias Systems Corporation was a pioneering Canadian software company best known for developing the high-end 3D graphics and animation software that became Autodesk Maya.
  • C. Quad Productions
    Quad Productions is a French film and advertising production company known for creating high-profile commercials and feature films.
  • D. Virtucon
    Virtucon is the fictional multinational conglomerate and front for Dr. Evil’s criminal organization in the Austin Powers film series.
  • E. Coktel Vision
    Coktel Vision was a French video game developer and publisher best known for its educational and adventure games in the 1980s and 1990s, including the Adibou/Adi series and Gobliiins.
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d799c3ed9c8190a3f5cdf1fe0e74a2 completed April 9, 2026, 12:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69e462d34c0081908067d91c163c118c completed April 19, 2026, 5:06 a.m.
Created at: April 8, 2026, 9:27 p.m.