Triple
T18784103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | modENCODE project |
E459329
|
entity |
| Predicate | dataRepository |
P1596
|
FINISHED |
| Object | UCSC Genome Browser tracks |
—
|
NE NERFINISHED |
How this triple was built (3 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: UCSC Genome Browser tracks | Statement: [modENCODE project, dataRepository, UCSC Genome Browser tracks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UCSC Genome Browser tracks Context triple: [modENCODE project, dataRepository, UCSC Genome Browser tracks]
-
A.
Genome Data Viewer
Genome Data Viewer is an NCBI web-based genome browser that allows users to visualize, explore, and analyze annotated genomic sequences and features.
-
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.
biomaRt package
The biomaRt package is an R/Bioconductor tool that provides programmatic access to a wide range of biological databases via the BioMart data management system, enabling flexible retrieval and integration of genomic annotation data.
-
D.
GenomicFeatures package
The GenomicFeatures package is a Bioconductor tool in R for representing, manipulating, and annotating genomic intervals and gene models using database-backed transcript annotations.
-
E.
RefSeq
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.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: UCSC Genome Browser tracks Target entity description: UCSC Genome Browser tracks are visual genomic data layers within the UCSC Genome Browser that display and integrate diverse experimental and annotation datasets, such as those generated by large-scale projects like modENCODE.
-
A.
Genome Data Viewer
Genome Data Viewer is an NCBI web-based genome browser that allows users to visualize, explore, and analyze annotated genomic sequences and features.
-
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.
biomaRt package
The biomaRt package is an R/Bioconductor tool that provides programmatic access to a wide range of biological databases via the BioMart data management system, enabling flexible retrieval and integration of genomic annotation data.
-
D.
GenomicFeatures package
The GenomicFeatures package is a Bioconductor tool in R for representing, manipulating, and annotating genomic intervals and gene models using database-backed transcript annotations.
-
E.
RefSeq
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.
- F. None of above. chosen
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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5977ffa648190be5f682bba47fb0a |
completed | April 20, 2026, 3:03 a.m. |
Created at: April 10, 2026, 11:52 a.m.