Triple

T20923334
Position Surface form Disambiguated ID Type / Status
Subject Robin Scherbatsky E515270 entity
Predicate friend P8712 FINISHED
Object Marshall Eriksen 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: Marshall Eriksen | Statement: [Robin Scherbatsky, friend, Marshall Eriksen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marshall Eriksen
Context triple: [Robin Scherbatsky, friend, Marshall Eriksen]
  • A. Marshall Eriksen chosen
    Marshall Eriksen is a kind-hearted, idealistic lawyer and devoted friend from the sitcom "How I Met Your Mother," known for his goofy humor and deep love for his wife Lily.
  • B. David Eriksen
    David Eriksen is a Norwegian music producer known for his work with various pop artists and groups, including on albums like "Wordshaker."
  • C. Carl Erickson
    Carl Erickson was an American screenwriter active in early 20th-century Hollywood, known for his work on several studio films during the 1930s.
  • D. Erik J. Sorensen
    Erik J. Sorensen is an American organic chemist known for his work in complex molecule synthesis and as a professor at Princeton University.
  • E. Andrew Hulshult
    Andrew Hulshult is a video game music composer best known for his heavy, metal-inspired soundtracks for modern retro-style shooters such as Dusk, Amid Evil, and various Doom-related projects.
  • 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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f64f767481909deccd77b50bf4ae completed April 21, 2026, 4 a.m.
Created at: April 16, 2026, 12:49 p.m.