Triple
T28708999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WMO space weather network |
E729773
|
entity |
| Predicate | sharesInformationOn |
P98094
|
FINISHED |
| Object | space weather impacts on Earth |
—
|
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: space weather impacts on Earth | Statement: [WMO space weather network, sharesInformationOn, space weather impacts on Earth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesInformationOn Context triple: [WMO space weather network, sharesInformationOn, space weather impacts on Earth]
-
A.
sharesInformationWith
Indicates that one entity communicates or provides information to another entity.
-
B.
providedInformationOn
Indicates that one entity supplied or communicated specific information or details to another entity.
-
C.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
D.
offersInformationOn
chosen
Indicates that one entity provides or makes available information about another entity or topic.
-
E.
collectsInformationOn
Indicates that one entity gathers or acquires data, facts, or details about another entity.
- 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_69f043e7d5a4819094b18aca10b1e024 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 28, 2026, 5:47 a.m.