Triple
T7581538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Younger Dryas cold event |
E179499
|
entity |
| Predicate | onsetRate |
P77983
|
FINISHED |
| Object | cooling over decades to a few years in Greenland ice-core records |
—
|
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: cooling over decades to a few years in Greenland ice-core records | Statement: [Younger Dryas cold event, onsetRate, cooling over decades to a few years in Greenland ice-core records]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onsetRate Context triple: [Younger Dryas cold event, onsetRate, cooling over decades to a few years in Greenland ice-core records]
-
A.
hasOnset
Indicates the point in time or condition at which a process, event, or state begins.
-
B.
spreadingRateType
Indicates the manner or category of how quickly or in what way something spreads or propagates.
-
C.
hasOnsetTypes
Indicates the types or categories of onset (e.g., how or when something begins) that are associated with a given entity or condition.
-
D.
eraOfIncreasedIntensity
Indicates a period during which the level or strength of a particular activity, condition, or phenomenon becomes significantly higher than before.
-
E.
typicalOnsetLocation
Indicates the anatomical location where a condition, symptom, or process most commonly begins or first appears.
- F. None of above. chosen
Provenance (4 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_69c69f327db881909a21ae3b156f8ded |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f97717048190b0ca1a74ed8a817e |
completed | March 27, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e04c2c8190a889d928515d9b8e |
completed | March 27, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69c6f8184bb08190b2f70545a6aa277c |
completed | March 27, 2026, 9:35 p.m. |
Created at: March 27, 2026, 3:52 p.m.