Triple

T17885972
Position Surface form Disambiguated ID Type / Status
Subject George Pérez E447201 entity
Predicate employer P7 FINISHED
Object CrossGen
CrossGen was an American comic book publisher active in the late 1990s and early 2000s, known for its creator-driven, interconnected fantasy and science fiction titles.
E1294353 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: CrossGen | Statement: [George Pérez, employer, CrossGen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CrossGen
Context triple: [George Pérez, employer, CrossGen]
  • A. Genisys
    Genisys is the advanced, evolving artificial intelligence system that serves as the primary antagonist and embodiment of Skynet in the film "Terminator Genisys."
  • B. InGen
    InGen is the fictional bioengineering corporation in the Jurassic Park franchise responsible for cloning dinosaurs and creating the dinosaur theme parks.
  • C. Geneta
    Geneta is a residential district and suburb within Södertälje Municipality in Sweden.
  • D. SGen (generational garbage collector)
    SGen is a generational garbage collector used by the Mono runtime to improve memory management performance and reduce pause times for managed applications.
  • E. Gigen
    Gigen is a village in northern Bulgaria known for its proximity to the archaeological remains of the ancient Roman town of Oescus on the Danube River.
  • 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: CrossGen
Triple: [George Pérez, employer, CrossGen]
Generated description
CrossGen was an American comic book publisher active in the late 1990s and early 2000s, known for its creator-driven, interconnected fantasy and science fiction titles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CrossGen
Target entity description: CrossGen was an American comic book publisher active in the late 1990s and early 2000s, known for its creator-driven, interconnected fantasy and science fiction titles.
  • A. Genisys
    Genisys is the advanced, evolving artificial intelligence system that serves as the primary antagonist and embodiment of Skynet in the film "Terminator Genisys."
  • B. InGen
    InGen is the fictional bioengineering corporation in the Jurassic Park franchise responsible for cloning dinosaurs and creating the dinosaur theme parks.
  • C. Geneta
    Geneta is a residential district and suburb within Södertälje Municipality in Sweden.
  • D. SGen (generational garbage collector)
    SGen is a generational garbage collector used by the Mono runtime to improve memory management performance and reduce pause times for managed applications.
  • E. Gigen
    Gigen is a village in northern Bulgaria known for its proximity to the archaeological remains of the ancient Roman town of Oescus on the Danube River.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c13bd288190a0302010ba4d0532 completed April 19, 2026, 9:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0313d994208190a6023cd9ba0602db completed May 12, 2026, 11:49 a.m.
NEDg Description generation batch_6a0314a4fa748190a63ecda792b7669a completed May 12, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0315a8d6e88190b6d532f22dd8088c completed May 12, 2026, 11:57 a.m.
Created at: April 10, 2026, 10:18 a.m.