Triple
T433080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rajya Sabha |
E9754
|
entity |
| Predicate | canRecommendAmendmentsTo |
P9444
|
FINISHED |
| Object | Money bills |
—
|
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: Money bills | Statement: [Rajya Sabha, canRecommendAmendmentsTo, Money bills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRecommendAmendmentsTo Context triple: [Rajya Sabha, canRecommendAmendmentsTo, Money bills]
-
A.
hasAmendments
Indicates that one entity (such as a document, law, or agreement) includes or is associated with one or more modifications, changes, or additions made after its original creation.
-
B.
canAmendBills
chosen
Indicates that an entity has the authority or ability to modify, revise, or propose changes to bills.
-
C.
amendmentRequires
Indicates that a particular amendment is necessary or must be applied in relation to another item, document, or condition.
-
D.
amendmentCount
Indicates the number of amendments that have been made to a given item, document, or entity.
-
E.
constitutionalChange
Indicates a formal modification, addition, or removal of provisions within a constitution or foundational legal framework.
- 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_69a2e801e1d48190b505d1dd336b52ac |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ef084840819080653004b674cba8 |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2edda55e88190b7c17ba94d7df1ce |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.