Triple
T21709474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iunius |
E535861
|
entity |
| Predicate | calendarTypeContext |
P5453
|
FINISHED |
| Object | pre-Julian Roman calendar |
—
|
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: pre-Julian Roman calendar | Statement: [Iunius, calendarTypeContext, pre-Julian Roman calendar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: calendarTypeContext Context triple: [Iunius, calendarTypeContext, pre-Julian Roman calendar]
-
A.
calendarType
chosen
Indicates the type or system of calendar associated with an entity (e.g., Gregorian, lunar, fiscal).
-
B.
calendarVariesBy
Indicates that the characteristics or values of a calendar (such as dates, events, or structure) change depending on another specified factor or context.
-
C.
calendarCategory
Indicates the classification or grouping assigned to calendar entries based on their type, purpose, or context.
-
D.
calendarFeature
Indicates that an entity provides or supports calendar-related functionality, such as scheduling, event management, or date-based organization.
-
E.
calendarDependence
Indicates that one event, action, or condition is determined, constrained, or triggered by a specific date, time, or calendar schedule.
- 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_69e0c46b44c0819088ab883ebd44e0e8 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efb5321d34819091f3cd03f7b407c0 |
completed | April 27, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69e6969113cc8190ab69855ef5667e4b |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:46 p.m.