Triple
T3830352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Special Masters of the U.S. Court of Federal Claims |
E90994
|
entity |
| Predicate | caseResolutionMethods |
P21258
|
FINISHED |
| Object | settlement |
—
|
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: settlement | Statement: [Office of Special Masters of the U.S. Court of Federal Claims, caseResolutionMethods, settlement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caseResolutionMethods Context triple: [Office of Special Masters of the U.S. Court of Federal Claims, caseResolutionMethods, settlement]
-
A.
resolutionMethod
Indicates the specific approach, technique, or process used to resolve a problem, conflict, or issue.
-
B.
methodOfDisputeResolution
Indicates the process or mechanism used to settle a disagreement or conflict between parties.
-
C.
resolutionMechanism
Indicates the method, process, or system used to resolve a conflict, issue, or discrepancy between entities.
-
D.
legalProcedureUsed
Indicates that a particular legal procedure or process is applied or employed in relation to a case, action, or legal matter.
-
E.
resolutionType
chosen
Indicates the specific manner or category by which an issue, event, or conflict is resolved or brought to a conclusion.
- 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_69aed960b538819096561c8ed448dec9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb8459f881908a2c91bb07e381ef |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74c2e04819094b94b3c0bac1806 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.