Triple
T23467108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PubChem BioAssay |
E569125
|
entity |
| Predicate | linkedTo |
P37
|
FINISHED |
| Object | PubChem Protein |
—
|
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: PubChem Protein | Statement: [PubChem BioAssay, linkedTo, PubChem Protein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PubChem Protein Context triple: [PubChem BioAssay, linkedTo, PubChem Protein]
-
A.
PubChem
PubChem is a free, publicly accessible database maintained by the National Institutes of Health that provides comprehensive information on the biological activities and chemical properties of small molecules and compounds.
-
B.
UniProt REST API
The UniProt REST API is a web service that allows programmatic access to UniProt’s protein sequence data and annotations for automated retrieval, analysis, and integration into bioinformatics workflows.
-
C.
Protein database
The Protein database is a curated collection of protein sequences and related functional, structural, and bibliographic information maintained by the National Center for Biotechnology Information (NCBI).
-
D.
PubChem Compound
PubChem Compound is a public database record type in the PubChem system that provides detailed chemical information about individual small molecules, including their structures, properties, and biological activities.
-
E.
Protein Information Resource
Protein Information Resource is a bioinformatics resource center that curates, annotates, and provides access to comprehensive protein sequence and functional information for the scientific community.
- 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: PubChem Protein Target entity description: PubChem Protein is a component of the PubChem database that provides detailed information on protein sequences and structures associated with chemical substances and bioassay data.
-
A.
PubChem
chosen
PubChem is a free, publicly accessible database maintained by the National Institutes of Health that provides comprehensive information on the biological activities and chemical properties of small molecules and compounds.
-
B.
UniProt REST API
The UniProt REST API is a web service that allows programmatic access to UniProt’s protein sequence data and annotations for automated retrieval, analysis, and integration into bioinformatics workflows.
-
C.
Protein database
The Protein database is a curated collection of protein sequences and related functional, structural, and bibliographic information maintained by the National Center for Biotechnology Information (NCBI).
-
D.
PubChem Compound
PubChem Compound is a public database record type in the PubChem system that provides detailed chemical information about individual small molecules, including their structures, properties, and biological activities.
-
E.
Protein Information Resource
Protein Information Resource is a bioinformatics resource center that curates, annotates, and provides access to comprehensive protein sequence and functional information for the scientific community.
- F. None of above.
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.