Triple
T25257039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USSD |
E633197
|
entity |
| Predicate | advantageOverApps |
P158796
|
FINISHED |
| Object | works without data connection |
—
|
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: works without data connection | Statement: [USSD, advantageOverApps, works without data connection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: advantageOverApps Context triple: [USSD, advantageOverApps, works without data connection]
-
A.
advantageOverCookies
Indicates a comparative relationship where one option, method, or entity is considered to have benefits or superiority when compared specifically to cookies.
-
B.
advantageOverPasswords
Indicates that one method, system, or approach provides benefits or improvements compared to traditional password-based authentication.
-
C.
technologyAdvantage
Indicates that one entity possesses a superior or more advanced technological capability compared to another entity.
-
D.
advantageOverSMS
Indicates that one communication method or system has benefits or superior qualities compared to SMS.
-
E.
applicationTool
Indicates that one entity is a tool or instrument used to apply, operate, or carry out the function of another entity.
- 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_69e75a922ad481908f4f1f884583cb42 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
| PDg | Predicate description generation | batch_69f48b9058d081908ec9af261ee092e2 |
completed | May 1, 2026, 11:16 a.m. |
Created at: April 21, 2026, 1:13 p.m.