Triple

T15413048
Position Surface form Disambiguated ID Type / Status
Subject Princess Peach E368639 entity
Predicate voiceActor P1507 FINISHED
Object Samantha Kelly E367852 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: Samantha Kelly | Statement: [Princess Peach, voiceActor, Samantha Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samantha Kelly
Context triple: [Princess Peach, voiceActor, Samantha Kelly]
  • A. Samantha Kelly chosen
    Samantha Kelly is an American voice actress best known for portraying Princess Peach and other characters in Nintendo’s Mario video game series.
  • B. Megyn Marie Kelly
    Megyn Marie Kelly is an American journalist, attorney, and media personality best known for her work as a news anchor on Fox News and later as a host on NBC.
  • C. Bridget Kelly
    Bridget Kelly is an American R&B singer and songwriter known for her work with Roc Nation and songs like "Special Delivery" and "Street Dreamin'."
  • D. Samantha Thompson
    Samantha Thompson is known as the daughter of American politician and former Illinois governor James R. Thompson.
  • E. Samantha Bond
    Samantha Bond is an English actress best known for playing Miss Moneypenny in the James Bond film series during the Pierce Brosnan era.
  • 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_69d85a16c68c819099c1b547fbc87b32 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03ea7561481909b04e613e2352f82 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a754d1881909ed322479bab460d completed May 9, 2026, 11:28 a.m.
Created at: April 10, 2026, 3:20 a.m.