Triple
T28263884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Labs |
E712650
|
entity |
| Predicate | testingApproach |
P43154
|
FINISHED |
| Object | A/B testing |
—
|
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: A/B testing | Statement: [Google Labs, testingApproach, A/B testing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testingApproach Context triple: [Google Labs, testingApproach, A/B testing]
-
A.
testingMethod
chosen
Indicates the procedure, technique, or approach used to perform a particular test or evaluation.
-
B.
testability
Indicates the degree to which a system, component, or behavior can be effectively and reliably tested to verify its correctness or performance.
-
C.
testCase
Indicates a relationship where a specific scenario, input set, or condition is used to verify, validate, or evaluate the behavior or correctness of a system, component, or function.
-
D.
mockupTesting
Indicates the process of evaluating and validating a design mockup by testing how well it meets intended requirements, usability, or user expectations.
-
E.
tests
Indicates that one entity examines, evaluates, or checks another entity or condition to determine its properties, performance, or correctness.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 11:13 p.m.