Triple
T17627886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Downpayment Plus Program |
E429895
|
entity |
| Predicate | targetsIncomeGroup |
P25350
|
FINISHED |
| Object | low-income households |
—
|
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: low-income households | Statement: [Downpayment Plus Program, targetsIncomeGroup, low-income households]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetsIncomeGroup Context triple: [Downpayment Plus Program, targetsIncomeGroup, low-income households]
-
A.
economicStatus
Indicates the financial or socioeconomic condition or standing of an entity relative to others or to defined economic criteria.
-
B.
incomeTargetingRequirement
chosen
Indicates that a condition or rule specifies required income levels or ranges that must be met for eligibility or targeting purposes.
-
C.
medianFamilyIncome2000USD
Indicates the median income earned by families in the year 2000, expressed in U.S. dollars.
-
D.
incomeMeasure
Indicates a relationship where one entity serves as a measure or metric of another entity’s income.
-
E.
medianHouseholdIncome
Indicates the typical (middle) value of income earned by households in a given area, such that half of households earn more and half earn less.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dbe3a308190a818d04f1a9b15f7 |
completed | April 19, 2026, 5:53 a.m. |
| PD | Predicate disambiguation | batch_69e3cdd7da34819099bc9481c5a79bab |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 5:52 a.m.