Triple
T25743031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawarden Castle (19th-century mansion) |
E648268
|
entity |
| Predicate | hasGroundsOpenToPublic |
P112457
|
FINISHED |
| Object | part of the estate |
—
|
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: part of the estate | Statement: [Hawarden Castle (19th-century mansion), hasGroundsOpenToPublic, part of the estate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGroundsOpenToPublic Context triple: [Hawarden Castle (19th-century mansion), hasGroundsOpenToPublic, part of the estate]
-
A.
hasPartOpenToPublic
chosen
Indicates that some portion or component of an entity is accessible for use or visitation by the general public.
-
B.
openToPublicDuring
Indicates that something is accessible or available for use by the general public during a specified time period or schedule.
-
C.
meetsOpenToPublic
Indicates that an entity satisfies the conditions required to be considered open and accessible to the general public.
-
D.
hasPublicSpaces
Indicates that an entity includes or provides areas that are accessible and usable by the general public.
-
E.
openedForPublic
Indicates that something has been made accessible or available for use, entry, or participation by the general public.
- 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_69e7ab306eec8190b05c312c6ab186b8 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620dc38088190b56b2b15ed75b3c2 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 22, 2026, 3:46 a.m.