Triple
T23473006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conserved Domain Database |
E570177
|
entity |
| Predicate | includesDataFrom |
P152409
|
FINISHED |
| Object | Pfam |
—
|
NE NERFINISHED |
How this triple was built (4 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: Pfam | Statement: [Conserved Domain Database, includesDataFrom, Pfam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pfam Context triple: [Conserved Domain Database, includesDataFrom, Pfam]
-
A.
Pfam domains
Pfam domains are conserved protein regions defined in the Pfam database that represent functional and structural units shared across different proteins.
-
B.
UniParc
UniParc is a comprehensive, non-redundant archive that stores and tracks all known unique protein sequences from multiple sources over time.
-
C.
InterPro entries
InterPro entries are curated records in the InterPro database that integrate diverse protein family, domain, and functional site signatures to provide unified functional and structural annotations for protein sequences.
-
D.
UniProtKB/TrEMBL
UniProtKB/TrEMBL is a computationally annotated section of the UniProt Knowledgebase that contains large-scale, unreviewed protein sequence records awaiting expert curation.
-
E.
Conserved Domain Database
The Conserved Domain Database is an NCBI-curated resource that catalogs and annotates conserved protein domains to support functional and evolutionary analysis of protein sequences.
- 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: Pfam Target entity description: Pfam is a widely used database of protein families and domains, each represented by multiple sequence alignments and hidden Markov models for functional and evolutionary analysis.
-
A.
Pfam domains
chosen
Pfam domains are conserved protein regions defined in the Pfam database that represent functional and structural units shared across different proteins.
-
B.
UniParc
UniParc is a comprehensive, non-redundant archive that stores and tracks all known unique protein sequences from multiple sources over time.
-
C.
InterPro entries
InterPro entries are curated records in the InterPro database that integrate diverse protein family, domain, and functional site signatures to provide unified functional and structural annotations for protein sequences.
-
D.
UniProtKB/TrEMBL
UniProtKB/TrEMBL is a computationally annotated section of the UniProt Knowledgebase that contains large-scale, unreviewed protein sequence records awaiting expert curation.
-
E.
Conserved Domain Database
The Conserved Domain Database is an NCBI-curated resource that catalogs and annotates conserved protein domains to support functional and evolutionary analysis of protein sequences.
- F. None of above.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesDataFrom Context triple: [Conserved Domain Database, includesDataFrom, Pfam]
-
A.
containsDataAbout
Indicates that one entity holds or includes information or records pertaining to another entity.
-
B.
supportsDataFrom
Indicates that one entity provides, validates, or underpins the data used or referenced by another entity.
-
C.
includedWith
Indicates that one entity is provided or packaged together as part of another entity.
-
D.
dataIncluded
Indicates that one data item or dataset contains, incorporates, or subsumes another as part of its contents.
-
E.
includes
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
- F. None of above. chosen
Provenance (4 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a70244208190bbd8f58ac16d4399 |
completed | April 29, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69f06201d33481909b5fd7b92d03e658 |
completed | April 28, 2026, 7:30 a.m. |
| PDg | Predicate description generation | batch_69f07cbbd7488190ab3c8ae7d0fb68bf |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 17, 2026, 5:57 p.m.