Triple
T2896764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunken Garden (Kensington Palace) |
E63957
|
entity |
| Predicate | hasPlantingScheme |
P9738
|
FINISHED |
| Object | seasonally changing flowers |
—
|
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: seasonally changing flowers | Statement: [Sunken Garden (Kensington Palace), hasPlantingScheme, seasonally changing flowers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlantingScheme Context triple: [Sunken Garden (Kensington Palace), hasPlantingScheme, seasonally changing flowers]
-
A.
plantingStyle
chosen
Indicates the method or arrangement used to plant entities in relation to each other or their environment.
-
B.
hasGardenType
Indicates that an entity possesses or is associated with a garden of a specified type.
-
C.
hasPlantSymbol
Indicates that an entity is associated with or represented by a particular plant as its symbolic emblem or sign.
-
D.
hasLandscaping
Indicates that an entity possesses or is associated with designed outdoor grounds or landscape features.
-
E.
isCultivatedAs
Indicates that one entity is intentionally grown, tended, or produced by another as a crop, resource, or cultivated organism.
- 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_69ab4c45822c8190830c5f2bb97bcfd0 |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe08e7b248190a6bb0f6999f99c23 |
completed | March 7, 2026, 8:23 a.m. |
| PD | Predicate disambiguation | batch_69abdd17bcdc8190aa47274a50ba4ad4 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:08 p.m.