Triple
T16088707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1992 Windsor Castle fire |
E390301
|
entity |
| Predicate | restorationDuration |
P98408
|
FINISHED |
| Object | about 5 years |
—
|
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: about 5 years | Statement: [1992 Windsor Castle fire, restorationDuration, about 5 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restorationDuration Context triple: [1992 Windsor Castle fire, restorationDuration, about 5 years]
-
A.
recoveryDuration
chosen
Indicates the length of time required for an entity to return to a normal or functional state after an event, condition, or disruption.
-
B.
restorationEnd
Indicates the point in time or condition at which a restoration process or restorative state comes to an end.
-
C.
restorationMeasure
Indicates that an action or intervention is undertaken to repair, rehabilitate, or return something to a previous or improved state.
-
D.
restorationType
Indicates the specific kind or category of restoration applied to an entity, such as the method, scope, or approach used to return it to a prior or improved state.
-
E.
wasRestoredAt
Indicates that an entity was brought back to a previous or improved state at a specific time or place.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1827ad7c88190b867da511cbfb7fa |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:59 a.m.