Triple
T37964540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Domaine national de Trianon |
E947101
|
entity |
| Predicate | significantGardenFeature |
P22782
|
FINISHED |
| Object | ornamental lakes |
—
|
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: ornamental lakes | Statement: [Domaine national de Trianon, significantGardenFeature, ornamental lakes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: significantGardenFeature Context triple: [Domaine national de Trianon, significantGardenFeature, ornamental lakes]
-
A.
gardenFeature
chosen
Indicates that one entity serves as a feature, element, or component within a garden associated with another entity.
-
B.
gardenValue
Indicates that one entity assigns or possesses a particular value, worth, or importance in relation to a garden.
-
C.
ornamentalFeature
Indicates that one entity serves as a decorative or embellishing feature of another entity.
-
D.
containsGarden
Indicates that one entity includes or has a garden within its area or boundaries.
-
E.
rockGardenDesignFeature
Indicates that something serves as a design feature or element within a rock garden.
- 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_69f76ef7062c819091bfacb7e83aa1e0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: May 3, 2026, 4:20 p.m.