Triple
T12352829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Michael's Church, Munich |
E294533
|
entity |
| Predicate | partiallyRebuiltIn |
P38760
|
FINISHED |
| Object | 20th 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: 20th century | Statement: [St. Michael's Church, Munich, partiallyRebuiltIn, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyRebuiltIn Context triple: [St. Michael's Church, Munich, partiallyRebuiltIn, 20th century]
-
A.
restoredInPart
Indicates that something has been brought back to a previous or improved state, but only partially rather than fully.
-
B.
partiallyRestored
chosen
Indicates that an entity has been brought back toward a previous or original state, but the restoration is incomplete or only partially achieved.
-
C.
reconstructedAsPartOf
Indicates that one entity has been rebuilt, restored, or recreated as a component or segment of another, larger whole.
-
D.
partiallyReusedAs
Indicates that one entity is used again as part of another entity, but only to a limited or incomplete extent rather than in its entirety.
-
E.
reopenedPartially
Indicates that an entity that was previously closed or inactive has been opened again, but only to a limited or incomplete extent.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8aa33c8190b22b7dff9559b8ed |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ecb5efc819086a3530282278bb1 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.