Triple
T776197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thuja |
E16390
|
entity |
| Predicate | hasSpecies |
P965
|
FINISHED |
| Object | Thuja koraiensis |
E16390
|
NE 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: Thuja koraiensis | Statement: [Thuja, hasSpecies, Thuja koraiensis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thuja koraiensis Context triple: [Thuja, hasSpecies, Thuja koraiensis]
-
A.
Thuja
chosen
Thuja is a genus of evergreen coniferous trees and shrubs commonly known as arborvitae, widely used in ornamental landscaping and hedging.
-
B.
Cryptomeria
Cryptomeria is a genus of large, evergreen coniferous trees native to East Asia, best known for the Japanese cedar widely used in timber and ornamental planting.
-
C.
Chamaecyparis
Chamaecyparis is a genus of evergreen coniferous trees commonly known as false cypresses, valued in horticulture and timber production.
-
D.
Korean pine
Korean pine is a large, long-lived conifer native to Northeast Asia, valued for its edible pine nuts, high-quality timber, and ecological importance in temperate forests.
-
E.
Zelkova
Zelkova is a small genus of deciduous trees in the elm family, valued as ornamentals and for bonsai, and native to parts of Europe and Asia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a49369a0848190af883934cee3db4c |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a733add08190bccd99cf9ec9096e |
completed | March 1, 2026, 8:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a67efa8dd481909097c551bf3a61dc |
completed | March 3, 2026, 6:26 a.m. |
Created at: March 1, 2026, 7:37 p.m.