Triple
T4267440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayward Fault |
E96858
|
entity |
| Predicate | regionPopulationExposed |
P32997
|
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: [Hayward Fault, regionPopulationExposed, millions of people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionPopulationExposed Context triple: [Hayward Fault, regionPopulationExposed, millions of people]
-
A.
targetedPopulation
Indicates the group of individuals or entities that an action, intervention, or effect is specifically directed toward.
-
B.
relativePopulation
Indicates the comparative size of one population relative to another, typically expressing how large, small, or proportionate it is.
-
C.
intendedCoveragePopulationShare
Indicates the proportion of a total population that a product, service, or intervention is intended or planned to cover.
-
D.
populationIncludes
Indicates that a population contains or encompasses the specified individual(s) or subgroup(s) as members or elements.
-
E.
populationCount
chosen
Indicates the total number of individuals in a specified group, area, or category.
- 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_69b34543f06c8190915ebb1a4574ffa9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34fce710481909d90ed4a3d150fde |
completed | March 12, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69b347f8dcb08190a725c1f7fb5a7466 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:07 p.m.