Triple
T29107837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UniParc |
E736814
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | UniProt database component |
C24488
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: UniProt database component Context triple: [UniParc, instanceOf, UniProt database component]
-
A.
biological database search system
A biological database search system is a software tool that enables users to efficiently query, retrieve, and analyze biological data (such as sequences, structures, and annotations) from one or more integrated databases.
-
B.
biological database
chosen
A biological database is an organized, searchable repository that stores, manages, and provides access to biological information such as sequences, structures, functions, and interactions of biomolecules and organisms.
-
C.
Critical Assessment of protein Structure Prediction experiment
A Critical Assessment of Protein Structure Prediction experiment is a systematic, blind evaluation of computational methods for predicting protein 3D structures by comparing their predictions against experimentally determined reference structures.
-
D.
EU database
An EU database is a structured, centralized repository managed by or for European Union institutions to store, organize, and provide controlled access to data relevant to EU policies, regulations, operations, or member states.
-
E.
bibliographic database provider
A bibliographic database provider is an organization or service that collects, curates, indexes, and delivers structured metadata about publications and scholarly works for search, discovery, and analysis.
- F. None of above.
Provenance (1 batch)
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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
Created at: April 28, 2026, 11:16 a.m.