Triple

T9810433
Position Surface form Disambiguated ID Type / Status
Subject Spotlight E238253 entity
Predicate productionCompany P490 FINISHED
Object Rocklin/Faust
Rocklin/Faust is a film production company best known for producing the Academy Award–winning investigative drama "Spotlight."
E822923 NE FINISHED

How this triple was built (4 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: Rocklin/Faust | Statement: [Spotlight, productionCompany, Rocklin/Faust]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rocklin/Faust
Context triple: [Spotlight, productionCompany, Rocklin/Faust]
  • A. Iron Felix
    Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
  • B. Jesus Lane
    Jesus Lane is a historic street in central Cambridge, England, known for its proximity to several colleges and notable university buildings.
  • C. Rider
    Rider is a British publishing imprint known for releasing works on spirituality, personal development, and thought-provoking non-fiction.
  • D. Rider
    Rider is a cross-platform integrated development environment by JetBrains, widely used for .NET and C# development.
  • E. Rider
    Rider, also known as Iskandar or Alexander the Great, is the charismatic and boisterous Servant of Waver Velvet in Fate/Zero, renowned for his overwhelming Noble Phantasm and kingly charisma.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rocklin/Faust
Triple: [Spotlight, productionCompany, Rocklin/Faust]
Generated description
Rocklin/Faust is a film production company best known for producing the Academy Award–winning investigative drama "Spotlight."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rocklin/Faust
Target entity description: Rocklin/Faust is a film production company best known for producing the Academy Award–winning investigative drama "Spotlight."
  • A. Iron Felix
    Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
  • B. Jesus Lane
    Jesus Lane is a historic street in central Cambridge, England, known for its proximity to several colleges and notable university buildings.
  • C. Rider
    Rider is a British publishing imprint known for releasing works on spirituality, personal development, and thought-provoking non-fiction.
  • D. Rider
    Rider is a cross-platform integrated development environment by JetBrains, widely used for .NET and C# development.
  • E. Rider
    Rider, also known as Iskandar or Alexander the Great, is the charismatic and boisterous Servant of Waver Velvet in Fate/Zero, renowned for his overwhelming Noble Phantasm and kingly charisma.
  • F. None of above. chosen

Provenance (5 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_69ca84defac48190abc1148804f184c1 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb220310c8190a16ca0b746f0ef7a completed April 2, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc5b4dd8819088c86946b4eb8a39 completed April 5, 2026, 2:43 a.m.
NEDg Description generation batch_69d1cd7f41448190b387109235dbc7f5 completed April 5, 2026, 2:48 a.m.
NED2 Entity disambiguation (via description) batch_69d1cdefca5c8190a673caca42aaa7d0 completed April 5, 2026, 2:50 a.m.
Created at: March 30, 2026, 8:30 p.m.