Triple

T16147623
Position Surface form Disambiguated ID Type / Status
Subject Jon Kamen E391826 entity
Predicate employer P7 FINISHED
Object RadicalMedia E391827 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: RadicalMedia | Statement: [Jon Kamen, employer, RadicalMedia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RadicalMedia
Context triple: [Jon Kamen, employer, RadicalMedia]
  • A. RadicalMedia chosen
    RadicalMedia is a multidisciplinary global production company known for creating innovative film, television, commercial, and digital content.
  • B. Mutual Newsreel
    Mutual Newsreel was a prominent radio news program that delivered national and international news coverage to American audiences during the golden age of network radio.
  • C. Radical Entertainment
    Radical Entertainment is a Canadian video game developer best known for creating titles such as The Simpsons: Hit & Run and the Prototype series.
  • D. Archive of Documentary Arts
    The Archive of Documentary Arts is a research collection dedicated to preserving and providing access to documentary photography, film, and other visual materials that chronicle social and cultural history.
  • E. Revolt TV
    Revolt TV is a music-oriented cable television network and media company founded by Sean "P. Diddy" Combs that focuses on hip-hop culture, news, and lifestyle programming.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d947e68819081b4b7c757ce71b6 completed April 17, 2026, 11:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffef2f49081909841a1f9bfbd622b completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 5:01 a.m.