Triple
T22675135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Term Asset-Backed Securities Loan Facility |
E560324
|
entity |
| Predicate | riskControl |
P49238
|
FINISHED |
| Object | haircuts on collateral |
—
|
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: haircuts on collateral | Statement: [Term Asset-Backed Securities Loan Facility, riskControl, haircuts on collateral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riskControl Context triple: [Term Asset-Backed Securities Loan Facility, riskControl, haircuts on collateral]
-
A.
riskManagement
Indicates the implementation of strategies and actions to identify, assess, and mitigate potential risks associated with an entity or activity.
-
B.
riskType
Indicates the category or nature of risk associated with an entity, event, or relationship.
-
C.
riskRequirement
Indicates that one entity specifies or imposes a required level or type of risk consideration that another entity must meet or address.
-
D.
riskMeasure
chosen
Indicates a quantitative assessment of the level of risk associated with an entity, event, or situation.
-
E.
riskBased
Indicates that something is determined, prioritized, or managed according to the level or assessment of risk involved.
- 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17823bd1881908958b0a8ba59e199 |
completed | April 29, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69ee62a6245881909506ff502da14137 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:11 p.m.