Triple
T32161100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krutitsy Metochion |
E821427
|
entity |
| Predicate | hasRestorer |
P203744
|
FINISHED |
| Object | Soviet conservation architects |
—
|
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: Soviet conservation architects | Statement: [Krutitsy Metochion, hasRestorer, Soviet conservation architects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRestorer Context triple: [Krutitsy Metochion, hasRestorer, Soviet conservation architects]
-
A.
hasRestoration
Indicates that an entity has undergone, is undergoing, or is associated with a process of repair, renewal, or restoration.
-
B.
hasUseAfterRestoration
Indicates that an entity is used or has a function specifically after it has been restored or repaired.
-
C.
hasRestorationPurpose
Indicates that something is intended or used for the purpose of restoring, repairing, or returning another thing to a previous or improved state.
-
D.
hasBeenRestored
Indicates that an entity has been returned to a previous or original state after damage, loss, or alteration.
-
E.
hasRestorationFocus
Indicates that something is primarily concerned with or directed toward restoration or repair.
- F. None of above. chosen
Provenance (4 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_69f34905e098819082191a6922a6d607 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01e27bb77c8190a7686b77a524f177 |
completed | May 11, 2026, 2:06 p.m. |
| PD | Predicate disambiguation | batch_6a01da2614788190b31db15539f5ba58 |
completed | May 11, 2026, 1:31 p.m. |
| PDg | Predicate description generation | batch_6a01e27af6488190af75efc2283d99b3 |
completed | May 11, 2026, 2:06 p.m. |
Created at: May 1, 2026, 12:32 a.m.