Triple
T23513912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Income-Contingent Repayment Plan (ICR) |
E572503
|
entity |
| Predicate | canBeSelectedThrough |
P130536
|
FINISHED |
| Object | loan servicer |
—
|
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: loan servicer | Statement: [Income-Contingent Repayment Plan (ICR), canBeSelectedThrough, loan servicer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeSelectedThrough Context triple: [Income-Contingent Repayment Plan (ICR), canBeSelectedThrough, loan servicer]
-
A.
isSelectedThrough
chosen
Indicates that an entity is chosen or determined by means of a specific process, method, or intermediary.
-
B.
hasSelectionFor
Indicates that one entity holds or specifies a chosen option, subset, or configuration on behalf of another entity.
-
C.
canChoose
Indicates that an entity has the ability or permission to select one option or entity from among alternatives.
-
D.
canBePassedTo
Indicates that one entity is capable of being transferred, handed over, or given to another entity.
-
E.
canBe
Indicates that one entity has the potential, permission, or capability to become, perform as, or be classified as 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa80174c819088c9c19fdcf2a133 |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:08 p.m.