Triple
T7476114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cox v. Louisiana |
E176636
|
entity |
| Predicate | hasUnitedStatesReportsCitation |
P16876
|
FINISHED |
| Object | 379 U.S. 536 |
—
|
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: 379 U.S. 536 | Statement: [Cox v. Louisiana, hasUnitedStatesReportsCitation, 379 U.S. 536]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnitedStatesReportsCitation Context triple: [Cox v. Louisiana, hasUnitedStatesReportsCitation, 379 U.S. 536]
-
A.
unitedStatesReportsPage
Indicates the specific page number within the United States Reports where a referenced legal case or decision is published.
-
B.
hasUSAN
Indicates that an entity has a specified United States Adopted Name (USAN), typically a nonproprietary name assigned to a pharmaceutical substance.
-
C.
countryReportsReviewed
Indicates that one entity has examined and evaluated official reports originating from a particular country.
-
D.
purchasedByUnitedStatesIn
Indicates that something was bought or acquired by the United States during a specified time period.
-
E.
firstPageInUnitedStatesReports
chosen
Indicates that a legal case or decision appears on the first page of a specified volume of the United States Reports.
- 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_69c69f236ce08190a04d7679f03b29b2 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f4ec85488190a1f7fb913e0fbe35 |
completed | March 27, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69c6f03d967081908a8e696ff9693b90 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:41 p.m.