Triple
T36923875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | castle of St. Aldobrand |
E913281
|
entity |
| Predicate | hasArchitecturalTypeInFiction |
P117060
|
FINISHED |
| Object | medieval fortress |
—
|
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: medieval fortress | Statement: [castle of St. Aldobrand, hasArchitecturalTypeInFiction, medieval fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArchitecturalTypeInFiction Context triple: [castle of St. Aldobrand, hasArchitecturalTypeInFiction, medieval fortress]
-
A.
architectInFiction
Indicates that an entity appears as an architect within a fictional work or narrative context.
-
B.
hasArchitecturalTheme
Indicates that one entity features or embodies a particular architectural style, motif, or design concept associated with another entity.
-
C.
hasFictionalType
chosen
Indicates that an entity is associated with or classified under a particular type or category that is fictional rather than real.
-
D.
hasFeatureInFiction
Indicates that a fictional work includes or portrays a particular feature, trait, or characteristic.
-
E.
hasArchitecturalFeature
Indicates that one entity possesses, includes, or is characterized by a specific architectural feature or element.
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe87b609888190913b0c3f787ecdba |
completed | May 9, 2026, 1:02 a.m. |
| PD | Predicate disambiguation | batch_69fe8731af48819092084f6f74bf052d |
completed | May 9, 2026, 1 a.m. |
Created at: May 3, 2026, 4:13 p.m.