Triple
T4078947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northgrippian |
E87430
|
entity |
| Predicate | climateProxyEvidence |
P49124
|
FINISHED |
| Object | Greenland ice cores |
—
|
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: Greenland ice cores | Statement: [Northgrippian, climateProxyEvidence, Greenland ice cores]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: climateProxyEvidence Context triple: [Northgrippian, climateProxyEvidence, Greenland ice cores]
-
A.
hasClimateRecord
chosen
Indicates that an entity possesses documented data or records about climate conditions or climate-related observations.
-
B.
climateDriver
Indicates a factor or process that significantly influences or drives changes in climate conditions.
-
C.
climatologicalSignificance
Indicates the degree to which something is important, influential, or relevant within the context of climate or long-term weather patterns.
-
D.
hasClimateContext
Indicates that something is associated with, influenced by, or relevant to climate-related conditions, factors, or considerations.
-
E.
climateChangeIndicator
Indicates that the subject serves as a sign, measure, or signal of the presence, extent, or impact of climate change on the related object or context.
- 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_69aed9435cf48190ad1da737c962d19d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc4e95b08190bd1ee8f6d3a9613c |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9082c2081908474f082a49bebc8 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.