Triple
T108413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Markets Tax Credit Program |
E2188
|
entity |
| Predicate | riskIfNoncompliance |
P7914
|
FINISHED |
| Object | recapture of tax credits |
—
|
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: recapture of tax credits | Statement: [New Markets Tax Credit Program, riskIfNoncompliance, recapture of tax credits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riskIfNoncompliance Context triple: [New Markets Tax Credit Program, riskIfNoncompliance, recapture of tax credits]
-
A.
riskLevel
Indicates the degree of potential harm, loss, or adverse outcome associated with a particular situation, action, or entity.
-
B.
riskProfile
Indicates the level and characteristics of potential risk associated with an entity, action, or situation.
-
C.
violatedPrinciple
Indicates that an entity has broken, disregarded, or acted contrary to a specified rule, norm, or guiding principle.
-
D.
restriction
Indicates a limiting condition or rule that constrains or controls what an entity can do, use, or access in relation to another entity or context.
-
E.
prohibits
Indicates that one entity forbids or disallows another entity from performing a specific action or being in a certain state.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25a1199ac8190ac65ffaaf45b4f5b |
completed | Feb. 28, 2026, 2:59 a.m. |
| PD | Predicate disambiguation | batch_69a2563e7188819091e9a94e071991d7 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a25a10d6448190bee47847d5c13b84 |
completed | Feb. 28, 2026, 2:59 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.