Triple
T20471065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermitian form |
E502192
|
entity |
| Predicate | orthogonalityCondition |
P76852
|
FINISHED |
| Object | x ⟂ y iff h(x,y)=0 |
—
|
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: x ⟂ y iff h(x,y)=0 | Statement: [Hermitian form, orthogonalityCondition, x ⟂ y iff h(x,y)=0]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orthogonalityCondition Context triple: [Hermitian form, orthogonalityCondition, x ⟂ y iff h(x,y)=0]
-
A.
orthogonalityProperty
chosen
Indicates that one entity possesses the property of being orthogonal (i.e., at right angles or having zero inner product) with respect to another entity or a given reference.
-
B.
orthonormalityRelation
Indicates that a set of vectors are mutually orthogonal and each has unit length with respect to a given inner product.
-
C.
perpendicularTo
Indicates that one entity is oriented at a right angle (90 degrees) to another entity.
-
D.
angleCondition
Indicates that a specified geometric relationship holds between angles, such as equality, inequality, or a particular angular constraint.
-
E.
orientedParallelTo
Indicates that one entity is parallel to another with a specified or consistent direction or orientation.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e699608d7c8190910217817e789915 |
completed | April 20, 2026, 9:23 p.m. |
| PD | Predicate disambiguation | batch_69e57679eb40819086142df3e39c928e |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:33 a.m.