Triple
T4470437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TRPO |
E98480
|
entity |
| Predicate | constraintType |
P35662
|
FINISHED |
| Object | trust region |
—
|
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: trust region | Statement: [TRPO, constraintType, trust region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constraintType Context triple: [TRPO, constraintType, trust region]
-
A.
constrainedBy
Indicates that one entity’s state, behavior, or possibilities are limited, restricted, or governed by another entity.
-
B.
designedToConstrain
Indicates that one entity is intentionally created or configured to limit, restrict, or control the behavior, range, or properties of another entity.
-
C.
restraintType
Indicates the specific kind or method of restraint applied in a given situation or relationship.
-
D.
typeOfCondition
chosen
Indicates that one condition is a specific kind, category, or subtype of another condition.
-
E.
invariantType
Indicates that one entity has a type or classification that remains constant or unchanged under specified conditions or transformations.
- 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_69b3454b4ae481908967426dd37284d6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b356fb69a0819099f0005779f4fcac |
completed | March 13, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69b3563bf4f8819081726cde3a34460b |
completed | March 13, 2026, 12:11 a.m. |
Created at: March 12, 2026, 11:34 p.m.