Triple
T29739731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Szydłów |
E752563
|
entity |
| Predicate | wallPreservationLevel |
P125898
|
FINISHED |
| Object | well-preserved |
—
|
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: well-preserved | Statement: [Szydłów, wallPreservationLevel, well-preserved]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wallPreservationLevel Context triple: [Szydłów, wallPreservationLevel, well-preserved]
-
A.
wallMaterial
Indicates that one entity is the material from which a wall or walls of another entity are constructed.
-
B.
wallThicknessOfKeep
Indicates the thickness of the walls of a keep in a fortification or castle.
-
C.
wallThicknessComparedTo
Indicates how the thickness of one wall relates to the thickness of another wall, typically in terms of being greater, equal, or less.
-
D.
wallCharacteristic
chosen
Indicates that a specified characteristic or property is attributed to a wall.
-
E.
wallFeature
Indicates that one entity functions as a structural or design feature associated with a wall of another entity.
- 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_69f0d62b064081908c1ae61cd68fb139 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f67336d44881908c3580e1ebb15bcf |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 7:47 p.m.