Triple
T23958367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johan Ernst Gunnerus |
E603856
|
entity |
| Predicate | usedTaxonomySystemOf |
P35623
|
FINISHED |
| Object | Carl Linnaeus |
—
|
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: Carl Linnaeus | Statement: [Johan Ernst Gunnerus, usedTaxonomySystemOf, Carl Linnaeus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedTaxonomySystemOf Context triple: [Johan Ernst Gunnerus, usedTaxonomySystemOf, Carl Linnaeus]
-
A.
usedTaxonomicSystem
chosen
Indicates that a particular taxonomic classification system was applied or followed when organizing or identifying the entities involved.
-
B.
taxonomicUsage
Indicates the way a taxonomic name is applied or used in a particular context, such as in a classification, identification, or reference.
-
C.
EUTaxonomy
Indicates that something is classified or evaluated according to the EU Taxonomy framework for environmentally sustainable economic activities.
-
D.
usesCategorySystem
Indicates that one entity organizes or classifies things according to a particular category system defined by another entity.
-
E.
typeOfTaxonomicAct
Indicates the specific kind of formal taxonomic action (such as naming, revising, or reclassifying a taxon) that is being recorded or referenced.
- 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_69e2954222288190a7323554d0cca8d7 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d0d85d348190946b578e1a1c3bcc |
completed | April 29, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:22 p.m.