Triple
T33985558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siegel upper half-space |
E871400
|
entity |
| Predicate | admitsAction |
P273
|
FINISHED |
| Object | Sp(2g,R) by fractional linear transformations |
—
|
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: Sp(2g,R) by fractional linear transformations | Statement: [Siegel upper half-space, admitsAction, Sp(2g,R) by fractional linear transformations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: admitsAction Context triple: [Siegel upper half-space, admitsAction, Sp(2g,R) by fractional linear transformations]
-
A.
admitsFrom
Indicates that one entity accepts or enrolls individuals coming from another specified source or institution.
-
B.
admissionAct
Indicates the act or event of formally allowing or accepting someone or something into a place, group, institution, or state.
-
C.
mayAdmit
Indicates that one entity has the permission or authority to allow another entity to enter, join, or be accepted into something.
-
D.
allows
chosen
Indicates that one entity grants permission, capability, or opportunity for another entity to perform an action or be in a certain state.
-
E.
enabledAction
Indicates that a particular action is permitted, activated, or available to be performed in the given context.
- 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_69f3499e964c8190b674b03f6f791b4b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.