Triple
T30085780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sargan test |
E764596
|
entity |
| Predicate | testStatisticDependsOn |
P168423
|
FINISHED |
| Object | sample size |
—
|
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: sample size | Statement: [Sargan test, testStatisticDependsOn, sample size]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testStatisticDependsOn Context triple: [Sargan test, testStatisticDependsOn, sample size]
-
A.
testStatisticDistribution
Indicates the probability distribution that a test statistic follows under specified conditions or hypotheses.
-
B.
hasTestStatistic
Indicates that a given test or analysis is associated with a specific numerical test statistic value.
-
C.
hasStatistics
Indicates that an entity is associated with one or more statistical measures, records, or summaries describing its quantitative properties or performance.
-
D.
sufficientStatistic
Indicates that one variable or set of variables contains all the information needed from the data to infer or estimate another variable or parameter, making the rest of the data irrelevant for that purpose.
-
E.
usedInStatistic
Indicates that something (such as a value, measure, or data item) is employed as part of the calculation or presentation of a particular statistic.
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67d6c7874819094e666ddb8c1059f |
completed | May 2, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
| PDg | Predicate description generation | batch_69f6749f205c81909d1aacf462912eee |
completed | May 2, 2026, 10:03 p.m. |
Created at: April 29, 2026, 7:04 p.m.