Triple
T23148924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Servian reforms |
E578268
|
entity |
| Predicate | createdClass |
P64281
|
FINISHED |
| Object | first class of citizens |
—
|
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: first class of citizens | Statement: [Servian reforms, createdClass, first class of citizens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdClass Context triple: [Servian reforms, createdClass, first class of citizens]
-
A.
exampleClass
Indicates that the subject belongs to, is categorized under, or serves as an instance of a particular class or type.
-
B.
createdEntityType
chosen
Indicates the type or category of entity that was produced or brought into existence as a result of the creation action.
-
C.
designClass
Indicates that one entity is the design or blueprint class from which the other entity is derived or instantiated.
-
D.
createdProgram
Indicates that an entity authored, developed, or produced a particular program (such as software or a coded application).
-
E.
createdFeature
Indicates that one entity brought another entity into existence or caused it to be produced as a feature.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ed0b76c8190ac61b949d88e9970 |
completed | April 29, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.