Triple
T1057060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riemann curvature tensor |
E22818
|
entity |
| Predicate | componentNotation |
P3759
|
FINISHED |
| Object | R^i_{ jkl} |
—
|
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: R^i_{ jkl} | Statement: [Riemann curvature tensor, componentNotation, R^i_{ jkl}]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: componentNotation
Context triple: [Riemann curvature tensor, componentNotation, R^i_{ jkl}]
-
A.
component1
Indicates that one entity functions as a constituent or part of another entity within a larger whole.
-
B.
distinguishingNotation
Indicates that one entity uses a specific notation or symbol to distinguish or differentiate another entity from similar ones.
-
C.
componentType
Indicates that one entity specifies or classifies the kind or category of component that another entity represents or uses.
-
D.
componentUnit
Indicates that one entity functions as a constituent or sub-unit that forms part of a larger composite entity.
-
E.
notationType
chosen
Indicates the specific system or style of notation used to represent or encode something (such as music, math, or language).
- 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_69a493dada0481909c43649f9843ea91 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4ba6e35ac8190802341c31bda0e3b |
completed | March 1, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69a4b7340a048190807363f19d17a58f |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.