Triple
T4849818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leeds Castle |
E108384
|
entity |
| Predicate | significantRestoration |
P59927
|
FINISHED |
| Object | 19th century |
—
|
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: 19th century | Statement: [Leeds Castle, significantRestoration, 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: significantRestoration Context triple: [Leeds Castle, significantRestoration, 19th century]
-
A.
majorRestorationLocation
Indicates the primary place where a significant restoration or refurbishment of an object, structure, or work was carried out.
-
B.
significantRevisionIn
Indicates that one entity represents a substantial or important change made within another entity, such as a major update or revision occurring in a larger work or version.
-
C.
restorationMeasure
Indicates that an action or intervention is undertaken to repair, rehabilitate, or return something to a previous or improved state.
-
D.
restorationEvent
Indicates an event in which something previously altered, damaged, or degraded is returned to a former or improved state.
-
E.
restorationGoal
Indicates that an action or plan is intended to return something to a previous, original, or improved state or condition.
- 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_69bd440a89548190a5f14ba6da6b97dc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddd17d881909f7731ff2b460e83 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2557388190a2d15571bacd24f3 |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6dda5e808190a26ec85e4499d8e4 |
completed | March 20, 2026, 3:55 p.m. |
Created at: March 20, 2026, 1:25 p.m.