Triple
T4144458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaunas Fortress |
E89348
|
entity |
| Predicate | partlyPreserved |
P35792
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Kaunas Fortress, partlyPreserved, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyPreserved Context triple: [Kaunas Fortress, partlyPreserved, yes]
-
A.
partiallyPreserved
chosen
Indicates that the referenced entity or object is only incompletely intact, with some parts missing, damaged, or lost while others remain.
-
B.
partiallyRestored
Indicates that an entity has been brought back toward a previous or original state, but the restoration is incomplete or only partially achieved.
-
C.
restoredInPart
Indicates that something has been brought back to a previous or improved state, but only partially rather than fully.
-
D.
partiallyDestroyed
Indicates that an entity has been damaged or ruined to a significant extent but not completely destroyed.
-
E.
partlyProtectedBy
Indicates that an entity is only partially safeguarded or covered by a specified protective measure, not fully protected.
- 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_69aed95785788190ae75bcf0cd1cafdf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af03a0f3408190adba7a8513bd3d12 |
completed | March 9, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69af018a54848190987f18c066c75068 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:43 p.m.