Triple
T30140331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seattle city budget |
E766109
|
entity |
| Predicate | includesSpendingFor |
P71941
|
FINISHED |
| Object | public safety |
—
|
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: public safety | Statement: [Seattle city budget, includesSpendingFor, public safety]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesSpendingFor Context triple: [Seattle city budget, includesSpendingFor, public safety]
-
A.
spendingRequires
Indicates that performing a spending action is contingent upon satisfying a specified requirement or condition.
-
B.
supportsSpendingCategory
Indicates that one entity allows, enables, or is compatible with making expenditures in a specified spending category.
-
C.
typeOfSpendingAffected
Indicates that a particular kind or category of spending is influenced, changed, or impacted by another factor or event.
-
D.
overseesSpendingOf
Indicates that one entity has authority to monitor, direct, or control how another entity’s funds or budget are used.
-
E.
expenditureFor
chosen
Indicates a relationship where a specific expenditure is made or allocated for a particular purpose, item, project, or entity.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a0058c341ac8190825067dc25158839 |
completed | May 10, 2026, 10:06 a.m. |
| PD | Predicate disambiguation | batch_6a005857249c81908b27587b84d84dbb |
completed | May 10, 2026, 10:05 a.m. |
Created at: April 29, 2026, 7:17 p.m.