Triple

T11290367
Position Surface form Disambiguated ID Type / Status
Subject John Romero E267307 entity
Predicate employer P7 FINISHED
Object Ion Storm E914386 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: Ion Storm | Statement: [John Romero, employer, Ion Storm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ion Storm
Context triple: [John Romero, employer, Ion Storm]
  • A. Ion Storm chosen
    Ion Storm was a late-1990s American video game development studio best known for titles like Deus Ex and Daikatana, and for its high-profile, turbulent history.
  • B. ByStorm Entertainment
    ByStorm Entertainment is a music record label known for signing and developing hip-hop and R&B artists.
  • C. Perfect Storm Entertainment
    Perfect Storm Entertainment is a film and television production company founded by director Justin Lin, known for its work on high-profile action and science fiction projects.
  • D. Point Breeze
    Point Breeze is a predominantly residential neighborhood in Pittsburgh, Pennsylvania, known for its historic homes, tree-lined streets, and proximity to Frick Park and the Frick Art Museum.
  • E. Point Breeze
    Point Breeze is a residential neighborhood in South Philadelphia known for its rowhouses, demographic diversity, and ongoing redevelopment and gentrification.
  • 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_69d6aac993a08190a6f36445ebaf9a43 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e98875a08190b8509fe55e49d52d completed April 9, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69e50a246a3c81909f4f1d32a1b1efeb completed April 19, 2026, 5 p.m.
Created at: April 8, 2026, 9:32 p.m.