Triple
T28581065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States v. Carolene Products Co. |
E723377
|
entity |
| Predicate | followedByCase |
P67498
|
FINISHED |
| Object | United States v. Darby |
—
|
NE NERFINISHED |
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: United States v. Darby | Statement: [United States v. Carolene Products Co., followedByCase, United States v. Darby]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followedByCase Context triple: [United States v. Carolene Products Co., followedByCase, United States v. Darby]
-
A.
subsequentCase
chosen
Indicates that one legal case follows another in time or procedural order, often relying on or referencing the earlier case.
-
B.
followedByClass
Indicates that one class or type is immediately succeeded by another class or type in a defined sequence or ordering.
-
C.
followedByResolution
Indicates that one event, state, or action is directly succeeded by a resolving event, state, or action in a sequence.
-
D.
followedByInSequence
Indicates that one event or element directly succeeds another in an ordered sequence.
-
E.
followedByComponent
Indicates that one component directly succeeds another component in a defined sequence or order.
- 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_69f01d7e97708190ae9e77ee66a68abd |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 28, 2026, 4:15 a.m.