Triple
T18784101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | modENCODE project |
E459329
|
entity |
| Predicate | dataRepository |
P1596
|
FINISHED |
| Object | modENCODE Data Coordination Center |
—
|
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: modENCODE Data Coordination Center | Statement: [modENCODE project, dataRepository, modENCODE Data Coordination Center]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: modENCODE Data Coordination Center Context triple: [modENCODE project, dataRepository, modENCODE Data Coordination Center]
-
A.
modENCODE project
The modENCODE project is a large-scale genomics initiative aimed at comprehensively identifying and annotating functional elements in model organisms such as Drosophila melanogaster and Caenorhabditis elegans.
-
B.
Hannover Unified Biobank
Hannover Unified Biobank is a centralized biomedical research biobank that collects, processes, and stores human biological samples and associated data to support translational and clinical research.
-
C.
Edico Genome
Edico Genome was a biotechnology company specializing in high-speed genomic data analysis through its DRAGEN bio-IT platform and FPGA-based acceleration technology.
-
D.
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.
-
E.
National Institute of Biomedical Genomics
The National Institute of Biomedical Genomics is an Indian research and training institution dedicated to advancing biomedical genomics, including human disease genomics and public health genomics.
- 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_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.