Triple
T32179099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Employee Retention Credit |
E821933
|
entity |
| Predicate | maximumCredit2020PerEmployee |
P185334
|
FINISHED |
| Object | 5000 USD |
—
|
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: 5000 USD | Statement: [Employee Retention Credit, maximumCredit2020PerEmployee, 5000 USD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumCredit2020PerEmployee Context triple: [Employee Retention Credit, maximumCredit2020PerEmployee, 5000 USD]
-
A.
maximumGrantAmount
Indicates the highest monetary value that can be awarded or granted under a specific grant, program, or agreement.
-
B.
incomeLimit
Indicates a specified maximum income threshold that must not be exceeded for a condition, eligibility, or rule to apply.
-
C.
maximumLoanAmountUSD
Indicates the highest amount of money, expressed in U.S. dollars, that can be loaned under a given agreement or condition.
-
D.
maximumAnnualPurchaseLimitPerSSN
Indicates the highest total amount that may be purchased within a year by any single individual, as identified by their Social Security Number.
-
E.
statutoryLimitPerIncidentUSD
Indicates the maximum monetary amount, in U.S. dollars, that is legally allowed to be claimed or paid for a single incident under a specific statute or regulation.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69f7be520f148190ba200bf3dbf40656 |
completed | May 3, 2026, 9:29 p.m. |
Created at: May 1, 2026, 12:34 a.m.