Triple
T10625503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | False Claims Act |
E250310
|
entity |
| Predicate | relatorShareRange |
P28992
|
FINISHED |
| Object | 15–30 percent of recovery depending on circumstances |
—
|
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: 15–30 percent of recovery depending on circumstances | Statement: [False Claims Act, relatorShareRange, 15–30 percent of recovery depending on circumstances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatorShareRange Context triple: [False Claims Act, relatorShareRange, 15–30 percent of recovery depending on circumstances]
-
A.
rangeOf
chosen
Indicates that one entity specifies the set of possible values (range) that another entity’s outputs or properties can take.
-
B.
hostRange
Indicates the range or set of different hosts that an organism, agent, or system can successfully inhabit, infect, or interact with.
-
C.
rangeRestricted
Indicates that the relationship or action applies only within a specified, limited subset of a broader domain or scope.
-
D.
sharesRoleWith
Indicates that two entities hold the same role or position within a given context or system.
-
E.
engagementRange
Indicates the distance or span within which an entity can effectively engage, interact with, or affect another entity.
- 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_69d6aa5993448190a493b790b8f85010 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6df80a30c81909f36fe221cf68822 |
completed | April 8, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69d6dd7fae088190973f70c69738af49 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 8:54 p.m.