Triple
T1420340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winter Palace |
E30208
|
entity |
| Predicate | restorationAfter |
P13045
|
FINISHED |
| Object | fire of 1837 |
—
|
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: fire of 1837 | Statement: [Winter Palace, restorationAfter, fire of 1837]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restorationAfter Context triple: [Winter Palace, restorationAfter, fire of 1837]
-
A.
restored
Indicates that an entity has returned another entity to a previous or improved state, condition, or position after damage, loss, or alteration.
-
B.
hasRestoration
chosen
Indicates that an entity has undergone, is undergoing, or is associated with a process of repair, renewal, or restoration.
-
C.
reconstructedAfter
Indicates that one entity has been rebuilt, restored, or reassembled following the occurrence or existence of another entity or event.
-
D.
restoredBy
Indicates that an entity has been returned to a previous or improved state through the actions or intervention of another entity.
-
E.
restorationEvent
Indicates an event in which something previously altered, damaged, or degraded is returned to a former 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_69a498fb823c8190a67ce4c4837e641a |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c40764ec8190b85de6befcb20dda |
completed | March 1, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69a4bf060b0081909ba00e6ac093a28b |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.