Triple
T32179097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Employee Retention Credit |
E821933
|
entity |
| Predicate | initialRule |
P14956
|
FINISHED |
| Object | employers could not claim ERC if they received a PPP loan |
—
|
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: employers could not claim ERC if they received a PPP loan | Statement: [Employee Retention Credit, initialRule, employers could not claim ERC if they received a PPP loan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialRule Context triple: [Employee Retention Credit, initialRule, employers could not claim ERC if they received a PPP loan]
-
A.
startRule
chosen
Indicates that a particular rule is the initial or entry rule from which a process, system, or evaluation begins.
-
B.
standardStartRule
Indicates that something begins or is initiated according to a defined standard or default rule.
-
C.
beganRule
Indicates that an entity started its period of ruling or governance over another entity or domain.
-
D.
startOfRule
Indicates that one element marks the beginning boundary or initial segment of a specified rule.
-
E.
firstCharacterRules
Indicates that the entity associated with the first character in a sequence has authority, control, or priority over the others.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 1, 2026, 12:34 a.m.