Triple
T21061785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Furst–Saxe–Sipser lower bounds |
E518865
|
entity |
| Predicate | provesLowerBoundFor |
P90269
|
FINISHED |
| Object | parity function |
—
|
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: parity function | Statement: [Furst–Saxe–Sipser lower bounds, provesLowerBoundFor, parity function]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: provesLowerBoundFor Context triple: [Furst–Saxe–Sipser lower bounds, provesLowerBoundFor, parity function]
-
A.
knownLowerBoundProvedBy
chosen
Indicates that a specific lower bound has been formally established or proven by a particular method, proof, or source.
-
B.
givesBoundOn
Indicates that one quantity provides an upper or lower limit (a bound) on the value or behavior of another quantity.
-
C.
isBoundedBelow
Indicates that every value in a set or function is greater than or equal to some fixed lower bound.
-
D.
isUpperBoundFor
Indicates that one value is greater than or equal to every element in a given set or collection, serving as an upper limit for them.
-
E.
boundedByApprox
Indicates that one quantity is constrained by another within an approximate or tolerance-based bound, rather than an exact strict limit.
- 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_69e0b505ef108190b25dd4033e2ff7eb |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6feb064a48190b892b78e27e8d0fa |
completed | April 21, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:38 p.m.