Triple

T1501947
Position Surface form Disambiguated ID Type / Status
Subject Katy Perry E33814 entity
Predicate instagramUsername P3718 FINISHED
Object katyperry E33814 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: katyperry | Statement: [Katy Perry, instagramUsername, katyperry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: katyperry
Context triple: [Katy Perry, instagramUsername, katyperry]
  • A. Katy Perry chosen
    Katy Perry is an American pop singer and songwriter known for chart-topping hits like "Firework" and "Roar" and her colorful, theatrical performances.
  • B. Kelly
    Kelly is the middle name of Richmond K. Turner, a prominent admiral in the United States Navy during World War II.
  • C. Kelly
    Kelly is a common Irish-origin surname widely used in English-speaking countries.
  • D. Kylie Jenner
    Kylie Jenner is an American media personality, cosmetics entrepreneur, and member of the Kardashian–Jenner family, widely known for her role on "Keeping Up with the Kardashians" and for founding Kylie Cosmetics.
  • E. Katy Hudson
    Katy Hudson is the self-titled 2001 Christian rock debut album of the artist later globally known as pop star Katy Perry.
  • 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_69a885f352a4819099b24ff15489dede completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a8872e41848190b35b37f32aef784f completed March 4, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad233464b08190927694a8f236227b completed March 8, 2026, 7:20 a.m.
Created at: March 4, 2026, 7:24 p.m.