Triple
T21494164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fermat primality test |
E530310
|
entity |
| Predicate | failsOn |
P91900
|
FINISHED |
| Object | Carmichael numbers for many bases |
—
|
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: Carmichael numbers for many bases | Statement: [Fermat primality test, failsOn, Carmichael numbers for many bases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: failsOn Context triple: [Fermat primality test, failsOn, Carmichael numbers for many bases]
-
A.
failsTo
Indicates that an expected action, process, or condition does not successfully occur or is not fulfilled.
-
B.
failsWhen
Indicates that a particular action, process, or condition does not succeed under the specified circumstances or triggers.
-
C.
failedOn
Indicates that an attempted action or process did not succeed when applied to a specific target, condition, or step.
-
D.
failsAtFirst
Indicates that an attempt at an action or task does not succeed on the first try.
-
E.
failsInGeneralFor
chosen
Indicates that an action, method, or approach does not succeed under typical or broad conditions, rather than only in specific edge cases.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea567244819091863350fedae3ae |
completed | April 23, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:23 p.m.