Triple
T3374882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olbrich Botanical Gardens |
E71042
|
entity |
| Predicate | Thai PavilionDecoration |
P8228
|
FINISHED |
| Object | gold leaf |
—
|
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: gold leaf | Statement: [Olbrich Botanical Gardens, Thai PavilionDecoration, gold leaf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Thai PavilionDecoration Context triple: [Olbrich Botanical Gardens, Thai PavilionDecoration, gold leaf]
-
A.
throneDecoration
Indicates that one entity serves as a decorative element or ornamentation for a throne associated with another entity.
-
B.
decoration
Indicates that one entity serves as an ornament or embellishing element for another entity, enhancing its appearance or style.
-
C.
decorationShape
Indicates the geometric or visual form that a decorative element or ornament takes in relation to the object it adorns.
-
D.
decorationSystem
Indicates a system or method used to apply, manage, or organize decorative elements in or around an entity.
-
E.
decorations
chosen
Indicates that one entity adds, provides, or serves as ornamental or decorative elements for another 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2e5fc6c81909ff582611751096d |
completed | March 8, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69ada433059881908e46f38cc5f40a32 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.