Triple
T2955674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vesuvius |
E79924
|
entity |
| Predicate | populationAtRisk |
P28398
|
FINISHED |
| Object | millions of people |
—
|
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: millions of people | Statement: [Vesuvius, populationAtRisk, millions of people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: populationAtRisk Context triple: [Vesuvius, populationAtRisk, millions of people]
-
A.
populationScale
Indicates the relative size or magnitude of a population, typically categorizing it into broad scale levels (e.g., small, medium, large).
-
B.
targetedPopulation
Indicates the group of individuals or entities that an action, intervention, or effect is specifically directed toward.
-
C.
populationRange
chosen
Indicates the numerical interval within which the size of a population falls.
-
D.
populationIncrease
Indicates that the number of individuals in a population has grown over a specified period of time.
-
E.
demographicScope
Indicates the specific population group or demographic segment to which something (e.g., a policy, study, product, or service) is targeted or applicable.
- 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_69ad8b1276588190a374a0b12e0f7bdf |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad99286ac8819084f02fbb0a1616d3 |
completed | March 8, 2026, 3:43 p.m. |
| PD | Predicate disambiguation | batch_69ad960c5c8881909d679912bd7d78f3 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:57 p.m.