Triple
T29107795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UniProtKB/Swiss-Prot |
E736813
|
entity |
| Predicate | hasCurationType |
P47400
|
FINISHED |
| Object | manually curated |
—
|
LITERAL FINISHED |
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: manually curated | Statement: [UniProtKB/Swiss-Prot, hasCurationType, manually curated]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCurationType Context triple: [UniProtKB/Swiss-Prot, hasCurationType, manually curated]
-
A.
curationType
chosen
Indicates the specific manner or method by which something has been selected, organized, or managed within a curated collection or context.
-
B.
isCurated
Indicates that an entity has been deliberately selected, organized, or managed according to specific criteria or standards.
-
C.
hasCuratorialModel
Indicates that one entity employs, follows, or is governed by a particular curatorial model defined by another entity.
-
D.
curationStatus
Indicates the current stage or condition of an item within a curation or review workflow (e.g., pending, approved, rejected, or in progress).
-
E.
hasCuratorialDiscipline
Indicates a relationship in which an entity is associated with a specific field or area of curatorial practice or expertise.
- F. None of above.
Provenance (3 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f7cec454a88190a9f3bbee2b856636 |
completed | May 3, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f7c8977c288190997a892ec5f756ed |
completed | May 3, 2026, 10:13 p.m. |
Created at: April 28, 2026, 11:16 a.m.