Triple
T8896834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fair Sentencing Act of 2010 |
E211824
|
entity |
| Predicate | changedSentencingRatio |
P85118
|
FINISHED |
| Object | crack-to-powder cocaine quantity ratio |
—
|
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: crack-to-powder cocaine quantity ratio | Statement: [Fair Sentencing Act of 2010, changedSentencingRatio, crack-to-powder cocaine quantity ratio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: changedSentencingRatio Context triple: [Fair Sentencing Act of 2010, changedSentencingRatio, crack-to-powder cocaine quantity ratio]
-
A.
createdSentencingDisparityBetween
Indicates that one entity’s actions or decisions caused or contributed to an unequal or inconsistent sentencing outcome between two or more parties.
-
B.
sentencedTo
Indicates that an authority has officially assigned a specific punishment or penalty to an entity, typically as the outcome of a legal or disciplinary process.
-
C.
numberOfPrisonSentences
Indicates the count of distinct prison sentences that have been imposed on a given individual or entity.
-
D.
numberOfOtherPrisonSentences
Indicates the count of additional prison sentences, separate from the primary one, that have been imposed on an individual.
-
E.
sentencingError
Indicates that there was a mistake or irregularity in the legal process of determining or imposing a sentence.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6424a8c08190aef2aa2079dd85f1 |
completed | April 1, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2bfb38819083d5eb1af8ccf4d6 |
completed | March 31, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69cc5cffe8ec819084c12770fe0578f2 |
completed | March 31, 2026, 11:47 p.m. |
Created at: March 30, 2026, 6:54 p.m.