Triple
T6663892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Branicki Palace |
E151544
|
entity |
| Predicate | hasGardenOrientation |
P72323
|
FINISHED |
| Object | towards river valley |
—
|
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: towards river valley | Statement: [Branicki Palace, hasGardenOrientation, towards river valley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGardenOrientation Context triple: [Branicki Palace, hasGardenOrientation, towards river valley]
-
A.
containsGarden
Indicates that one entity includes or has a garden within its area or boundaries.
-
B.
hasGardenType
Indicates that an entity possesses or is associated with a garden of a specified type.
-
C.
hasGardenSquare
Indicates that an entity includes, is adjacent to, or is otherwise associated with a garden square.
-
D.
gardenFeature
Indicates that one entity serves as a feature, element, or component within a garden associated with another entity.
-
E.
gateOrientation
Indicates the directional alignment or facing direction of a gate relative to a reference frame or coordinate system.
- F. None of above. chosen
Provenance (4 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_69c687f5fac48190a09e4838d9c6b45d |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
| PDg | Predicate description generation | batch_69c6ce72809c8190be85f6e42ca1c8ea |
completed | March 27, 2026, 6:37 p.m. |
Created at: March 27, 2026, 2:02 p.m.