Triple
T21523171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geminids |
E531026
|
entity |
| Predicate | annualActivityEnd |
P84725
|
FINISHED |
| Object | mid-December |
—
|
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: mid-December | Statement: [Geminids, annualActivityEnd, mid-December]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: annualActivityEnd Context triple: [Geminids, annualActivityEnd, mid-December]
-
A.
endOfActivity
Indicates that a particular activity has reached its completion or final point in time.
-
B.
activeYearsEndTime
Indicates the point in time when an entity’s period of activity or operation comes to an end.
-
C.
activatedAnnuallyUntil
Indicates that an action or state is activated once each year and continues to do so repeatedly up to, but not beyond, a specified end date.
-
D.
typicallyEndsAt
chosen
Indicates that an event, process, or activity most commonly or usually concludes at a particular time, place, or state.
-
E.
annualFrom
Indicates that something recurs or is calculated on a yearly basis starting from a specified point in time.
- 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee884db3ac81909e77d22d607ac72d |
completed | April 26, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:26 p.m.