Triple

T22454183
Position Surface form Disambiguated ID Type / Status
Subject Mike Tollin E555069 entity
Predicate notableWork P4 FINISHED
Object Good Burger NE NERFINISHED

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: Good Burger | Statement: [Mike Tollin, notableWork, Good Burger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Good Burger
Context triple: [Mike Tollin, notableWork, Good Burger]
  • A. Good Burger chosen
    Good Burger is a 1997 comedy film based on a popular Nickelodeon sketch, following two quirky fast-food employees as they try to save their burger joint from a rival chain.
  • B. Good Burger 2
    Good Burger 2 is a 2023 comedy film sequel that reunites Kenan Thompson and Kel Mitchell as fast-food workers in a revival of their popular 1990s Nickelodeon movie.
  • C. Joyful Burger Street
    Joyful Burger Street is a fictional street in the Jelmore setting, likely characterized by fast-food eateries and a lively, upbeat atmosphere.
  • D. Die Burger
    Die Burger is a prominent Afrikaans-language daily newspaper published in South Africa, known for its regional and national news coverage.
  • E. Beyond Burger
    Beyond Burger is a popular plant-based burger patty designed to closely mimic the taste and texture of beef while being made entirely from non-animal ingredients.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4e2bd4819083e5bed44e9776c6 completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.