Triple

T21026757
Position Surface form Disambiguated ID Type / Status
Subject Nature Communications E517959 entity
Predicate isIndexedIn P6000 FINISHED
Object PubMed 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: PubMed | Statement: [Nature Communications, isIndexedIn, PubMed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PubMed
Context triple: [Nature Communications, isIndexedIn, PubMed]
  • A. PubMed chosen
    PubMed is a free search engine providing access to a vast database of biomedical and life sciences literature maintained by the U.S. National Library of Medicine.
  • B. PubMed Central
    PubMed Central is a free digital archive of biomedical and life sciences journal literature maintained by the U.S. National Institutes of Health’s National Library of Medicine.
  • C. Europe PubMed Central
    Europe PubMed Central is a regional, open-access repository that provides access to biomedical and life sciences research articles, mirroring and extending the content of PubMed Central for European users.
  • D. MEDLINE
    MEDLINE is a premier bibliographic database of life sciences and biomedical information maintained by the U.S. National Library of Medicine.
  • E. Embase
    Embase is a comprehensive biomedical and pharmacological bibliographic database widely used for systematic literature searches, particularly in drug and clinical research.
  • 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_69e0b503275c8190afd9a163f997c709 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc7d93908190a2c29a4051fb5acc completed April 21, 2026, 4:26 a.m.
Created at: April 16, 2026, 1:55 p.m.