Triple
T5425666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E(n) |
E121355
|
entity |
| Predicate | isClosedSubgroupOf |
P63684
|
FINISHED |
| Object | affine group of R^n |
—
|
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: affine group of R^n | Statement: [E(n), isClosedSubgroupOf, affine group of R^n]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isClosedSubgroupOf Context triple: [E(n), isClosedSubgroupOf, affine group of R^n]
-
A.
isSubnetworkOf
Indicates that one network is a contained, subordinate, or component part of another, larger network.
-
B.
isSemidirectProductOf
Indicates that a group is constructed as a semidirect product of two subgroups, where one subgroup acts on the other via automorphisms in a way that generalizes the direct product.
-
C.
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.
-
D.
haveSubgroups
Indicates that an entity is organized into smaller constituent groups that are part of it.
-
E.
notClosedUnder
Indicates that applying the operation or relation to elements of a set can produce results that do not belong to that set, so the set is not closed under that operation or relation.
- 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_69bd463b58d88190b258261573de9e91 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8911a7348190ad9378a248190f07 |
completed | March 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69bd846b8bdc81909dcdc2a3084226f2 |
completed | March 20, 2026, 5:31 p.m. |
| PDg | Predicate description generation | batch_69bd8910de688190aa0cd80627849a60 |
completed | March 20, 2026, 5:51 p.m. |
Created at: March 20, 2026, 2:06 p.m.