Triple
T2346977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deposit Insurance Fund |
E45152
|
entity |
| Predicate | canBorrowFrom |
P38885
|
FINISHED |
| Object | U.S. Treasury under certain conditions |
—
|
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: U.S. Treasury under certain conditions | Statement: [Deposit Insurance Fund, canBorrowFrom, U.S. Treasury under certain conditions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBorrowFrom Context triple: [Deposit Insurance Fund, canBorrowFrom, U.S. Treasury under certain conditions]
-
A.
canCollect
Indicates that one entity has the ability or permission to gather, receive, or take possession of another entity.
-
B.
canBring
Indicates that one entity has the ability or permission to bring another entity or item to a particular place or context.
-
C.
hasBorrowingsFrom
Indicates that one entity has taken, adopted, or derived elements (such as features, ideas, or content) from another entity.
-
D.
availableWith
Indicates that one entity can be obtained, accessed, or used in conjunction with another entity.
-
E.
canUse
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
- F. None of above. chosen
Provenance (4 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_69a88917935081909b755dbf38e81024 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abcade3c808190ab3803538ccbe620 |
completed | March 7, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69abc59616a8819099711834e6f1ccd6 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcadd2a0c8190b6973d390e98bd66 |
completed | March 7, 2026, 6:51 a.m. |
Created at: March 4, 2026, 7:52 p.m.