Triple
T11215010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dehn twist |
E265413
|
entity |
| Predicate | inverse |
P9300
|
FINISHED |
| Object | inverse Dehn twist |
—
|
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: inverse Dehn twist | Statement: [Dehn twist, inverse, inverse Dehn twist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inverse Context triple: [Dehn twist, inverse, inverse Dehn twist]
-
A.
inverseImage
Indicates the mapping from a set of outputs back to all inputs that are related to those outputs under a given function or relation.
-
B.
reversed
chosen
Indicates that the direction or order of a previously defined relationship or sequence between entities is inverted.
-
C.
opposite
Indicates that one entity is positioned or oriented directly across from, or in a contrary or reverse relation to, another entity.
-
D.
verse
Indicates that one entity is in opposition or conflict against another, as in a competitive or adversarial relationship.
-
E.
in
Indicates that one entity is located within the spatial, temporal, or conceptual bounds of another entity.
- 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8e8eef48190932a85784ce15c86 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.