Triple
T594346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eurodollar futures |
E17345
|
entity |
| Predicate | hedgingHorizon |
P12018
|
FINISHED |
| Object | short-term interest rate exposures up to several years ahead |
—
|
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: short-term interest rate exposures up to several years ahead | Statement: [Eurodollar futures, hedgingHorizon, short-term interest rate exposures up to several years ahead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hedgingHorizon Context triple: [Eurodollar futures, hedgingHorizon, short-term interest rate exposures up to several years ahead]
-
A.
timeHorizonOfLoans
Indicates the length of time over which loans are scheduled to be outstanding or repaid.
-
B.
hasEventHorizon
Indicates that an object possesses an event horizon, a boundary beyond which events cannot affect an outside observer.
-
C.
holdsFor
chosen
Indicates that a particular relationship or condition remains true over a specified interval or duration of time.
-
D.
aimsToBalance
Indicates an intention or effort by one entity to bring multiple elements, forces, or conditions into a state of equilibrium.
-
E.
hasTradingHours
Indicates that an entity operates or is available for trading during specified time periods.
- 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_69a49379d09c8190ac7e00b24e2810b1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49bd15c5881909b59ed4c88687e7b |
completed | March 1, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69a494ceeb7881909a91ed1a35d5bf0a |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.