Triple
T29446905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IS curve |
E746876
|
entity |
| Predicate | isHeldConstant |
P136294
|
FINISHED |
| Object | price level in the basic IS–LM model |
—
|
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: price level in the basic IS–LM model | Statement: [IS curve, isHeldConstant, price level in the basic IS–LM model]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isHeldConstant Context triple: [IS curve, isHeldConstant, price level in the basic IS–LM model]
-
A.
variableHeldConstant
chosen
Indicates that a particular variable is maintained at a fixed value and not allowed to change while other factors or conditions are varied or analyzed.
-
B.
usesConstant
Indicates that one entity makes use of a specific constant value defined or provided by another entity.
-
C.
isHeldEvery
Indicates that an event or activity occurs regularly on every specified time interval or occasion.
-
D.
includesConstant
Indicates that one entity contains or explicitly references a specific constant value within its definition or structure.
-
E.
isHeldDuring
Indicates that one event, activity, or state occurs within the temporal span of another event or period.
- 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_69f0a7a230488190b44a97fe3d16f731 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f66b21ea908190ae69b3f802fadab1 |
completed | May 2, 2026, 9:22 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:28 p.m.