Triple

T17863205
Position Surface form Disambiguated ID Type / Status
Subject Sylvia Tilly E446124 entity
Predicate friendOf P8712 FINISHED
Object Paul Stamets 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: Paul Stamets | Statement: [Sylvia Tilly, friendOf, Paul Stamets]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Stamets
Context triple: [Sylvia Tilly, friendOf, Paul Stamets]
  • A. Paul Stamets chosen
    Paul Stamets is an American mycologist, author, and advocate for the study and use of fungi in medicine, ecology, and environmental restoration.
  • B. Stamets
    Stamets is the surname of Paul Stamets, a prominent American mycologist and advocate for the study and use of fungi in medicine and ecology.
  • C. Dennis McKenna
    Dennis McKenna is an American ethnopharmacologist, author, and researcher known for his work on psychoactive plants and his collaborations with his brother Terence McKenna in the study of psychedelics.
  • D. Michael T. Sauer
    Michael T. Sauer was an American judge best known for presiding over high-profile criminal cases in Los Angeles County.
  • E. Paul Grilley
    Paul Grilley is a yoga teacher best known for popularizing Yin Yoga and for his influential work on anatomy and skeletal variation in yoga practice.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e49791b0c08190b04a426bd274065d completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.