Triple
T23466948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GEO Profiles |
E569122
|
entity |
| Predicate | usesDataFrom |
P399
|
FINISHED |
| Object | GEO DataSets |
—
|
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: GEO DataSets | Statement: [GEO Profiles, usesDataFrom, GEO DataSets]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GEO DataSets Context triple: [GEO Profiles, usesDataFrom, GEO DataSets]
-
A.
GEO DataSets
chosen
GEO DataSets is a public NCBI repository that organizes and provides access to curated gene expression and other functional genomics experiment data.
-
B.
Gene Expression Omnibus
Gene Expression Omnibus is a public NCBI repository that archives and freely distributes high-throughput gene expression and other functional genomics data submitted by the research community.
-
C.
GEO reports
GEO reports are flagship United Nations environmental assessment publications that periodically evaluate the state of the global environment, emerging trends, and policy options for sustainable development.
-
D.
BioProject database
The BioProject database is an NCBI resource that organizes and links together data from large-scale biological research projects, such as genome sequencing and functional genomics studies.
-
E.
dbGaP
dbGaP (the Database of Genotypes and Phenotypes) is a National Institutes of Health (NIH) repository that archives and distributes data from studies investigating the interaction of genotype and phenotype in humans.
- 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_69e2458ebd808190b3298163132cfb0b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a6fc35c48190a67614fb4170f15b |
completed | April 29, 2026, 6:36 a.m. |
Created at: April 17, 2026, 5:54 p.m.