Triple
T37731110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croome Park |
E940155
|
entity |
| Predicate | restorationWorkBy |
P128862
|
FINISHED |
| Object | National Trust |
—
|
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: National Trust | Statement: [Croome Park, restorationWorkBy, National Trust]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restorationWorkBy Context triple: [Croome Park, restorationWorkBy, National Trust]
-
A.
reconstructionWorkBy
Indicates that a reconstruction project or effort is carried out, overseen, or authored by a specific agent or entity.
-
B.
restorationProject
Indicates a project whose purpose is to repair, renew, or return something to a previous or improved condition.
-
C.
hasRestorationWorkBy
chosen
Indicates that an entity has undergone restoration work carried out by a specified agent or party.
-
D.
reconstructionWork
Indicates that an entity is engaged in or associated with activities to rebuild, restore, or repair something that was damaged, destroyed, or altered.
-
E.
restorationUse
Indicates the use of something specifically for the purpose of restoring, repairing, or returning another entity to a previous or improved state.
- 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_69f76edefd048190a32212c5c3919531 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:18 p.m.