Triple
T10639498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claudius (nomen) |
E250683
|
entity |
| Predicate | declensionClass |
P48358
|
FINISHED |
| Object | second declension masculine |
—
|
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: second declension masculine | Statement: [Claudius (nomen), declensionClass, second declension masculine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: declensionClass Context triple: [Claudius (nomen), declensionClass, second declension masculine]
-
A.
hasAdjectiveDeclensionType
Indicates that an adjective is associated with a specific pattern or type of grammatical declension.
-
B.
hasNounDeclensionType
chosen
Indicates that a noun is associated with a specific grammatical declension pattern or type.
-
C.
morphologicalClass
Indicates the classification of an entity based on its morphological form or structural pattern.
-
D.
declination
Indicates the angular deviation of one direction or object from a reference plane or axis, typically measuring how far it is tilted or offset.
-
E.
hasNounClassSystem
Indicates that an entity possesses a grammatical system in which nouns are categorized into distinct classes that affect their agreement with other elements in the language.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfcbe5308190986bba438d19e852 |
completed | April 8, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69d6dd83b114819098e84dc658e82d7e |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:04 p.m.