Triple
T35197333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SmartPay charge card program |
E1016297
|
entity |
| Predicate | transactionScope |
P199604
|
FINISHED |
| Object | official government business only |
—
|
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: official government business only | Statement: [SmartPay charge card program, transactionScope, official government business only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transactionScope Context triple: [SmartPay charge card program, transactionScope, official government business only]
-
A.
reservationScope
Indicates the extent or range within which a reservation applies or is valid.
-
B.
modificationScope
Indicates the extent or range within which a change, adjustment, or alteration applies to an entity or its attributes.
-
C.
lockScope
Indicates the extent or range within which a lock applies to resources or operations, defining what is protected by that locking action.
-
D.
syncScope
Indicates that two or more processes, threads, or operations are coordinated to occur within the same synchronization context or boundary.
-
E.
trialScope
Indicates that an action, condition, or rule applies only within the defined boundaries or context of a specific trial or experimental instance.
- F. None of above. chosen
Provenance (4 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_69f76dde814c8190a71f60d514a424a4 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff48199b1c8190bb05872f8a4f4673 |
completed | May 9, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69ff4746b1cc8190854f70a124df7d04 |
completed | May 9, 2026, 2:40 p.m. |
| PDg | Predicate description generation | batch_69ff4818bb288190b4a27576fad18e23 |
completed | May 9, 2026, 2:43 p.m. |
Created at: May 3, 2026, 4:02 p.m.