Triple
T22041877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dyrham Park |
E544654
|
entity |
| Predicate | parklandDesignation |
P89445
|
FINISHED |
| Object | Grade II* registered park and 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: Grade II* registered park and garden | Statement: [Dyrham Park, parklandDesignation, Grade II* registered park and garden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parklandDesignation Context triple: [Dyrham Park, parklandDesignation, Grade II* registered park and garden]
-
A.
parkDesignation
chosen
Indicates that an area or location has been officially designated or classified as a park.
-
B.
earthDesignation
Indicates that an entity has a specific name or label assigned to it for use in an Earth-based or human-centric context.
-
C.
designatedAsNationalPark
Indicates that an area has been officially assigned the legal status and protections of a national park by an authorized governing body.
-
D.
environmentDesignation
Indicates that an entity is assigned a specific environmental classification or status within a given context.
-
E.
designatedAsWildlifeRefuge
Indicates that an area has been officially assigned the status and protections of a wildlife refuge.
- 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_69e11e32445c8190ab97089b48a130bb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12829c1c081909edc7544242c9c7a |
completed | April 28, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:25 p.m.