Triple
T35879059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loudoun Castle |
E1037456
|
entity |
| Predicate | majorRebuildingDate |
P145013
|
FINISHED |
| Object | early 1800s |
—
|
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: early 1800s | Statement: [Loudoun Castle, majorRebuildingDate, early 1800s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorRebuildingDate Context triple: [Loudoun Castle, majorRebuildingDate, early 1800s]
-
A.
rebuiltOrModifiedDuring
chosen
Indicates that an existing entity was reconstructed, renovated, or otherwise significantly altered during a specified time period or event.
-
B.
rebuiltOn
Indicates that one entity has been reconstructed, restored, or built again on, over, or using the foundation, structure, or basis of another entity.
-
C.
redevelopmentDate
Indicates the date on which an existing structure, area, or asset is scheduled for or has undergone redevelopment.
-
D.
reconstructionOrRestorationDate
Indicates the date on which an entity was reconstructed or restored after damage, alteration, or deterioration.
-
E.
renovatedAfter
Indicates that one entity was renovated at a later time than another entity.
- 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_69f76e1e701c8190a4990d4978ce4fe6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff9bed58dc8190a204816d4ed6c32c |
completed | May 9, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69ff9b69653c81908ab0d88055a66a88 |
completed | May 9, 2026, 8:39 p.m. |
Created at: May 3, 2026, 4:06 p.m.