Triple
T27496792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strobilanthes kunthiana |
E694038
|
entity |
| Predicate | bloomEffect |
P16366
|
FINISHED |
| Object | carpets hillsides in blue |
—
|
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: carpets hillsides in blue | Statement: [Strobilanthes kunthiana, bloomEffect, carpets hillsides in blue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bloomEffect Context triple: [Strobilanthes kunthiana, bloomEffect, carpets hillsides in blue]
-
A.
visualEffect
chosen
Indicates that one entity produces, modifies, or is associated with a particular visual effect on another entity or within a scene.
-
B.
resolutionEffect
Indicates the outcome, consequence, or change that results from a particular resolution, decision, or problem-solving action.
-
C.
ashCloudEffect
Indicates the impact or consequences that an ash cloud has on other entities, conditions, or processes.
-
D.
landscapeEffect
Indicates how a particular landscape or terrain influences or modifies the outcome, behavior, or characteristics of another entity or process.
-
E.
projectionEffect
Indicates the visual or spatial transformation produced when something is projected from one surface, medium, or viewpoint onto another.
- 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_69ef538370888190b1ddf53bb4831188 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62ec0087c819092b5a19c4bf6a3d0 |
completed | May 2, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:09 p.m.