Triple
T28880739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starobinsky R^2 inflation model |
E732409
|
entity |
| Predicate | addsTerm |
P2920
|
FINISHED |
| Object | R^2 term in the gravitational action |
—
|
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: R^2 term in the gravitational action | Statement: [Starobinsky R^2 inflation model, addsTerm, R^2 term in the gravitational action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addsTerm Context triple: [Starobinsky R^2 inflation model, addsTerm, R^2 term in the gravitational action]
-
A.
hasTerm
chosen
Indicates that an entity includes, is associated with, or is defined by a specific term or condition.
-
B.
componentTerm
Indicates that one term functions as a component or constituent part of another term within a larger conceptual or structural whole.
-
C.
usedTerm
Indicates that one entity employed, referenced, or applied a particular term in some context.
-
D.
ownedTermBy
Indicates that a specific term is possessed, controlled, or held in ownership by a particular entity.
-
E.
laterTerm
Indicates that one term occurs after another term in a temporal or sequential order.
- 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_69f05b06807c81909b4bbd4c20403a2b |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65a6d639481909e661755a5838a47 |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 7:43 a.m.