Triple
T3655042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomb of Akbar the Great |
E77507
|
entity |
| Predicate | hasGardenLayout |
P12538
|
FINISHED |
| Object | Persian-style garden |
—
|
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: Persian-style garden | Statement: [Tomb of Akbar the Great, hasGardenLayout, Persian-style garden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGardenLayout Context triple: [Tomb of Akbar the Great, hasGardenLayout, Persian-style garden]
-
A.
hasGardenType
chosen
Indicates that an entity possesses or is associated with a garden of a specified type.
-
B.
containsGarden
Indicates that one entity includes or has a garden within its area or boundaries.
-
C.
hasLandscaping
Indicates that an entity possesses or is associated with designed outdoor grounds or landscape features.
-
D.
gardenFeature
Indicates that one entity serves as a feature, element, or component within a garden associated with another entity.
-
E.
landscapeDesignedBy
Indicates that a particular landscape or outdoor environment was planned, created, or shaped by a specific designer or design entity.
- 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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3baf57c8190b72b5d1b910d9db6 |
completed | March 8, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69adb84650148190bf79231105e58d7f |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.