Triple

T22931921
Position Surface form Disambiguated ID Type / Status
Subject UniGene E569464 entity
Predicate relatedTo P37 FINISHED
Object RefSeq 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: RefSeq | Statement: [UniGene, relatedTo, RefSeq]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RefSeq
Context triple: [UniGene, relatedTo, RefSeq]
  • A. RefSeq chosen
    RefSeq is a curated, non-redundant collection of reference DNA, RNA, and protein sequences maintained by the National Center for Biotechnology Information for use in genome annotation and biological research.
  • B. Ensembl
    Ensembl is a comprehensive genome annotation and browsing platform that provides detailed, regularly updated genomic data for a wide range of species.
  • C. GenBank
    GenBank is a comprehensive public database of nucleotide sequences and their associated annotation, widely used as a primary resource for genetic and genomic research.
  • D. RSEQ
    RSEQ is the governing body that organizes and oversees student sports and athletic competitions across Quebec’s educational institutions.
  • E. UniRef
    UniRef is a set of clustered protein sequence databases derived from UniProt that group similar sequences to reduce redundancy and speed up sequence similarity searches.
  • 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_69e2458f7d008190901dccbaebeaba24 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1813260608190bb9e1ca704c7e12f completed April 29, 2026, 3:55 a.m.
Created at: April 17, 2026, 3:44 p.m.