Triple

T21289786
Position Surface form Disambiguated ID Type / Status
Subject Paul Schimmel E524754 entity
Predicate coFounded P104 FINISHED
Object Alkermes 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: Alkermes | Statement: [Paul Schimmel, coFounded, Alkermes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alkermes
Context triple: [Paul Schimmel, coFounded, Alkermes]
  • A. Alkermes chosen
    Alkermes is a biopharmaceutical company that develops innovative medicines for central nervous system disorders and other serious chronic diseases.
  • B. Jazz Pharmaceuticals
    Jazz Pharmaceuticals is a biopharmaceutical company specializing in developing and commercializing innovative medicines for sleep disorders, oncology, and rare diseases.
  • C. Cephalon
    Cephalon was a biopharmaceutical company known for developing and marketing specialty drugs in areas such as central nervous system disorders, pain management, and oncology.
  • D. Biogen
    Biogen is a major American biotechnology company known for developing therapies for neurological and neurodegenerative diseases.
  • E. Vertex Pharmaceuticals
    Vertex Pharmaceuticals is a biotechnology company best known for developing transformative therapies for cystic fibrosis and other serious diseases using a precision medicine approach.
  • 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d9467881908ec5b1dec76e6f5d completed April 21, 2026, 8:35 a.m.
Created at: April 16, 2026, 4:03 p.m.