Triple
T4960757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pasterze Glacier |
E111400
|
entity |
| Predicate | averageAnnualRetreatRate |
P61449
|
FINISHED |
| Object | several metres per year |
—
|
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: several metres per year | Statement: [Pasterze Glacier, averageAnnualRetreatRate, several metres per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageAnnualRetreatRate Context triple: [Pasterze Glacier, averageAnnualRetreatRate, several metres per year]
-
A.
averageSlipRate
Indicates the typical rate at which displacement or movement occurs along a fault or interface over a specified period of time.
-
B.
averageSpreadingRate
Indicates the typical rate at which something (such as a phenomenon, substance, or influence) expands or propagates over a given distance or time.
-
C.
averageRecurrenceInterval
Indicates the typical time span between successive occurrences of the same type of event.
-
D.
displacementRate
Indicates the rate at which an entity’s position changes over time relative to a reference point or frame.
-
E.
averageAnnualSnowfall
Indicates the typical amount of snow that falls in a given location over the course of a year, averaged across multiple years.
- 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_69bd4419393c819086319a6fe4bf8542 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd72e49b048190bac55d9e7a6f7963 |
completed | March 20, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69bd71447fe88190bb62c5e8753da7a7 |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd72e1b7cc8190b2e621fdf8f22e38 |
completed | March 20, 2026, 4:16 p.m. |
Created at: March 20, 2026, 1:32 p.m.