Triple
T11215011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dehn twist |
E265413
|
entity |
| Predicate | inverseProperty |
P21517
|
FINISHED |
| Object | inverse is the twist in the opposite direction |
—
|
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 is the twist in the opposite direction | Statement: [Dehn twist, inverseProperty, inverse is the twist in the opposite direction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inverseProperty Context triple: [Dehn twist, inverseProperty, inverse is the twist in the opposite direction]
-
A.
isInverseOf
chosen
Indicates that one relation reverses the direction of another, so that if the original relates A to B, its inverse relates B to A.
-
B.
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.
-
C.
identityRelation
Indicates that two entities are in fact the very same entity, not merely similar or equivalent.
-
D.
valueRelation
Indicates a comparative or associative relationship between the values or magnitudes of two or more entities.
-
E.
identifiesPropertyOf
Indicates that one entity specifies or denotes a particular property or attribute belonging to 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.