Triple
T1212923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Trust |
E26042
|
entity |
| Predicate | opensToPublic |
P4864
|
FINISHED |
| Object | historic buildings |
—
|
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: historic buildings | Statement: [National Trust, opensToPublic, historic buildings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opensToPublic Context triple: [National Trust, opensToPublic, historic buildings]
-
A.
openedForPublic
Indicates that something has been made accessible or available for use, entry, or participation by the general public.
-
B.
openToPublicSince
Indicates that an entity has been accessible or available for use by the general public starting from a specified point in time.
-
C.
openStatus
Indicates whether an entity (such as a place, service, or resource) is currently open or available for use.
-
D.
opens
chosen
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
-
E.
isOpenTo
Indicates that one entity is receptive, willing, or available to consider, accept, or engage with another entity or proposal.
- 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_69a4948331fc8190b531ac9bec71c491 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bde6cb608190b77fc5c47083e4b7 |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb62a7c08190a79dcb6ff72ac99b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.