Triple
T11862161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LM curve |
E282184
|
entity |
| Predicate | shiftsLeftWhen |
P34686
|
FINISHED |
| Object | real money supply decreases |
—
|
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: real money supply decreases | Statement: [LM curve, shiftsLeftWhen, real money supply decreases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shiftsLeftWhen Context triple: [LM curve, shiftsLeftWhen, real money supply decreases]
-
A.
shiftedUnder
Indicates that one entity has been moved or displaced to a position beneath another entity.
-
B.
marksShiftToward
chosen
Indicates a change or transition from one state, condition, or position toward another, highlighting the direction or trend of that shift.
-
C.
leftPosition
Indicates that one entity is located to the left side of another entity in space or ordering.
-
D.
offsets
Indicates that one entity counterbalances, compensates for, or reduces the effect, value, or impact of another.
-
E.
hasDynamicShifts
Indicates that something exhibits changes or transitions in state, intensity, or behavior over time rather than remaining constant.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69b16bc8190999a0c1240f9ce6a |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.