Triple

T18751869
Position Surface form Disambiguated ID Type / Status
Subject Dame Kay Davies E458544 entity
Predicate title P38 FINISHED
Object FMedSci 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: FMedSci | Statement: [Dame Kay Davies, title, FMedSci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FMedSci
Context triple: [Dame Kay Davies, title, FMedSci]
  • A. FMedSci chosen
    FMedSci is the post-nominal title for Fellows of the Academy of Medical Sciences in the United Kingdom, recognizing significant contributions to medical science.
  • B. SciMed
    SciMed is the official abbreviation for the Faculty of Science and Medicine at the University of Fribourg, a multidisciplinary faculty combining scientific and medical education and research.
  • C. Science (journal)
    Science is a leading peer‑reviewed academic journal that publishes cutting-edge research across all scientific disciplines.
  • D. Minerva Medica
    Minerva Medica is a healing aspect of the Roman goddess Minerva, venerated particularly in connection with medicinal and therapeutic functions.
  • E. Medscape
    Medscape is a leading online platform that provides medical news, clinical information, and educational resources for healthcare professionals.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e579ed4e6881908791f2a6250010a6 completed April 20, 2026, 12:57 a.m.
Created at: April 10, 2026, 11:51 a.m.