Triple

T9872909
Position Surface form Disambiguated ID Type / Status
Subject John Ratzenberger E240000 entity
Predicate voicedCharacter P2000 FINISHED
Object Fritz E274391 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: Fritz | Statement: [John Ratzenberger, voicedCharacter, Fritz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fritz
Context triple: [John Ratzenberger, voicedCharacter, Fritz]
  • A. Fritz
    Fritz is an individual known primarily as the offspring of Fifi.
  • B. Fritz chosen
    Fritz is the hunchbacked assistant to Dr. Frankenstein in the 1931 horror film "Frankenstein," known for helping to procure the monster’s body parts and brain.
  • C. Fritz
    Fritz London was a German-born theoretical physicist best known for his pioneering work on quantum mechanics and the theory of intermolecular forces, including London dispersion forces.
  • D. Fritz
    Fritz is a masculine given name of German origin commonly used in German-speaking countries.
  • E. Fritz
    Fritz is one of the animatronic macaw hosts in Walt Disney’s Enchanted Tiki Room attraction at Disney theme parks.
  • 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_69ca84e8a0788190b9061811d50fd554 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb3f754008190abe3fe034b42908e completed April 2, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e46f18148190a36af7e7d7487205 completed April 5, 2026, 4:26 a.m.
Created at: March 30, 2026, 8:37 p.m.