Triple

T4748154
Position Surface form Disambiguated ID Type / Status
Subject Soul Men E105411 entity
Predicate storyBy P1955 FINISHED
Object Matthew Stone E243327 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: Matthew Stone | Statement: [Soul Men, storyBy, Matthew Stone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Stone
Context triple: [Soul Men, storyBy, Matthew Stone]
  • A. Matthew Stone chosen
    Matthew Stone is a common name shared by several notable individuals, including professionals in fields such as art, entertainment, and academia.
  • B. Matt Stone
    Matt Stone is an American animator, writer, producer, and actor best known as the co-creator of the satirical television series "South Park."
  • C. Scott Storch
    Scott Storch is an American record producer and songwriter known for his influential work in hip-hop and pop music, crafting hits for artists like Dr. Dre, Beyoncé, and 50 Cent.
  • D. Jorma Taccone
    Jorma Taccone is an American writer, director, actor, and comedian best known as a member of the comedy trio The Lonely Island and for his work on Saturday Night Live.
  • E. Paul Lieberstein
    Paul Lieberstein is an American writer, producer, and actor best known for playing HR representative Toby Flenderson and serving as a key writer and showrunner on the U.S. version of "The Office."
  • 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_69bd43f07fa48190954317d01600994a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64c567288190a420e6825ee72822 completed March 20, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43b24440819081f3932eb6b68b48 completed March 21, 2026, 7:07 a.m.
Created at: March 20, 2026, 1:20 p.m.