Triple
T32179098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Employee Retention Credit |
E821933
|
entity |
| Predicate | laterRule |
P200342
|
FINISHED |
| Object | employers could claim ERC and PPP but not on the same wages |
—
|
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 claim ERC and PPP but not on the same wages | Statement: [Employee Retention Credit, laterRule, employers could claim ERC and PPP but not on the same wages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterRule Context triple: [Employee Retention Credit, laterRule, employers could claim ERC and PPP but not on the same wages]
-
A.
laterPolicy
Indicates that one policy occurs or becomes effective after another policy in time.
-
B.
laterUnderRuleOf
Indicates that one entity came to be governed or ruled by another entity at a later point in time.
-
C.
laterIn
Indicates that one event, state, or time point occurs after another in temporal order.
-
D.
laterBasedOn
Indicates that one event, state, or version occurs or is established after another, using the earlier one as its basis or reference point.
-
E.
laterWithin
Indicates that one event or time point occurs later than another while still falling within a specified temporal interval or boundary.
- 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_69ff84202eb081908ae21a54a4414d68 |
completed | May 9, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69ff833065e4819098579129d4ee17d3 |
completed | May 9, 2026, 6:55 p.m. |
| PDg | Predicate description generation | batch_69ff841f2f2081908d72d4f878c538a0 |
completed | May 9, 2026, 6:59 p.m. |
Created at: May 1, 2026, 12:34 a.m.