Triple

T20301023
Position Surface form Disambiguated ID Type / Status
Subject Pascal Soriot E505478 entity
Predicate previousEmployer P1910 FINISHED
Object Genentech 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: Genentech | Statement: [Pascal Soriot, previousEmployer, Genentech]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Genentech
Context triple: [Pascal Soriot, previousEmployer, Genentech]
  • A. Genentech chosen
    Genentech is a pioneering American biotechnology company known for developing groundbreaking therapies and being one of the first firms to apply genetic engineering to medicine.
  • B. Amgen
    Amgen is a leading American biopharmaceutical company known for developing innovative therapies in areas such as oncology, nephrology, and inflammatory diseases.
  • C. Janssen Biotech
    Janssen Biotech is a biopharmaceutical company known for developing and manufacturing innovative biologic therapies, including the blockbuster monoclonal antibody Remicade.
  • D. Merck Life Science
    Merck Life Science is the life science business of Merck KGaA, providing products and technologies for research, biotechnology, and pharmaceutical development worldwide.
  • E. Genmab
    Genmab is a Danish biotechnology company specializing in the development of antibody-based cancer therapies.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6770c700c81909da247cef0d0f1eb completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:17 a.m.