Triple
T4518435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 31 March Incident |
E103207
|
entity |
| Predicate | calendarNote |
P14069
|
FINISHED |
| Object | Named for 31 March 1325 in the Rumi 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: Named for 31 March 1325 in the Rumi calendar | Statement: [31 March Incident, calendarNote, Named for 31 March 1325 in the Rumi calendar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: calendarNote Context triple: [31 March Incident, calendarNote, Named for 31 March 1325 in the Rumi calendar]
-
A.
calendarFeature
Indicates that an entity provides or supports calendar-related functionality, such as scheduling, event management, or date-based organization.
-
B.
dateNote
chosen
Indicates a note, comment, or annotation that is specifically associated with a particular date or dating information.
-
C.
calendarContribution
Indicates a relationship where an entity adds to, modifies, or otherwise participates in the creation or maintenance of a calendar or scheduled events.
-
D.
agendaItem
Indicates that something is an item or entry on a planned agenda or schedule of topics to be addressed.
-
E.
calendarFunction
Indicates a relationship where an entity serves as a function or operation within a calendar system, such as computing or manipulating dates, times, or calendar-related events.
- 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd57465a10819086866e29f7a6eb02 |
completed | March 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69bd521abea48190b3e758a1f98dd55e |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:02 p.m.