Triple
T3357427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drakensteyn Castle |
E70638
|
entity |
| Predicate | becameRoyalResidence |
P46590
|
FINISHED |
| Object | 1963 |
—
|
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: 1963 | Statement: [Drakensteyn Castle, becameRoyalResidence, 1963]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: becameRoyalResidence Context triple: [Drakensteyn Castle, becameRoyalResidence, 1963]
-
A.
becameRoyalResidenceIn
chosen
Indicates that a place or building started serving as an official royal residence at a specified point in time.
-
B.
usedAsRoyalResidenceUntil
Indicates that something served as a royal residence up to a specified point in time.
-
C.
servedAsImperialResidenceFrom
Indicates that an entity functioned as an imperial residence starting from a specified point in time.
-
D.
formerCapitalResidence
Indicates that an entity once served as the official residence associated with a capital (such as a capital city or seat of government) but no longer holds that status.
-
E.
monarchUsedAsResidence
Indicates that a monarch uses or has used a particular place as their residence.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb244435c81908e35d2aa36ec4f46 |
completed | March 8, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.