Triple
T16144913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3 October Vereeniging |
E391753
|
entity |
| Predicate | usesCalendarDate |
P112456
|
FINISHED |
| Object | 3 October each year |
—
|
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: 3 October each year | Statement: [3 October Vereeniging, usesCalendarDate, 3 October each year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCalendarDate Context triple: [3 October Vereeniging, usesCalendarDate, 3 October each year]
-
A.
usesCalendar
Indicates that an entity employs or relies on a calendar system for organizing, tracking, or scheduling dates and events.
-
B.
usesCalendarEvent
chosen
Indicates that one entity makes use of, interacts with, or relies on a specific calendar event.
-
C.
dateDetermination
Indicates the process or criteria by which a specific date is identified, calculated, or assigned in relation to an event or condition.
-
D.
hasCalendarFunction
Indicates that an entity possesses or supports a calendar-related capability or functionality.
-
E.
hasCalendarCustom
Indicates that an entity is associated with a customized or non-default calendar configuration or behavior.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d92b0408190a010bd8e5193aa36 |
completed | April 17, 2026, 11:46 a.m. |
| PD | Predicate disambiguation | batch_69e182885bc08190822ae7e8a4b8ac1f |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:01 a.m.