Triple

T8182389
Position Surface form Disambiguated ID Type / Status
Subject Mack Swain E191093 entity
Predicate employer P7 FINISHED
Object Keystone Studios E147987 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: Keystone Studios | Statement: [Mack Swain, employer, Keystone Studios]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keystone Studios
Context triple: [Mack Swain, employer, Keystone Studios]
  • A. Keystone Studios chosen
    Keystone Studios was an early 20th-century American film studio famous for its slapstick comedies and for launching Charlie Chaplin’s screen career.
  • B. Keystone Pictures
    Keystone Pictures is a film production company best known for producing the family sports comedy movie "Air Bud."
  • C. Skyline Studios
    Skyline Studios is a professional recording studio known for hosting music production and album recording sessions.
  • D. Annapurna Studios
    Annapurna Studios is a prominent Indian film production and post-production company based in Hyderabad, widely recognized for its role in shaping Telugu cinema.
  • E. Sky Studios
    Sky Studios is the original programming and production arm of European broadcaster Sky, known for creating high-profile television series and films across drama, comedy, and other genres.
  • 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_69ca82c4538081909404325aa5639483 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4c4db8748190aa785e0c70fac497 completed March 31, 2026, 4:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbf8e8f0c819096f449760ce0d240 completed April 1, 2026, 6:47 a.m.
Created at: March 30, 2026, 5:40 p.m.