Triple
T35879068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loudoun Castle |
E1037456
|
entity |
| Predicate | themeParkBranding |
P185272
|
FINISHED |
| Object | Loudoun Castle Theme Park |
—
|
NE NERFINISHED |
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: Loudoun Castle Theme Park | Statement: [Loudoun Castle, themeParkBranding, Loudoun Castle Theme Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: themeParkBranding Context triple: [Loudoun Castle, themeParkBranding, Loudoun Castle Theme Park]
-
A.
themeParkStyle
Indicates that something is designed, presented, or experienced in the manner or aesthetic typical of a theme park.
-
B.
themeParkAttractionAt
Indicates that a specific theme park attraction is located at or associated with a particular theme park or site.
-
C.
themeParkConnection
Indicates a relationship where two or more entities are connected through a theme park, such as by location, operation, partnership, or shared attractions.
-
D.
themeParkAttraction
Indicates that something is an attraction or ride located within a theme park.
-
E.
inspiredThemePark
Indicates that one entity (such as a work, brand, or concept) served as the creative basis or inspiration for the design, attractions, or overall concept of a theme park.
- 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_69f76e1e701c8190a4990d4978ce4fe6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
| PDg | Predicate description generation | batch_69f7bbf812cc8190a16917c5daaff2df |
completed | May 3, 2026, 9:19 p.m. |
Created at: May 3, 2026, 4:06 p.m.