Triple
T22104342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandyavarta |
E546247
|
entity |
| Predicate | hasShapeRelation |
P146996
|
FINISHED |
| Object | swastika |
—
|
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: swastika | Statement: [Nandyavarta, hasShapeRelation, swastika]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShapeRelation Context triple: [Nandyavarta, hasShapeRelation, swastika]
-
A.
hasRelation
Indicates that there exists some specified relationship or association between two entities.
-
B.
hasArchitecturalRelation
Indicates a structural or spatial relationship between architectural elements, such as how buildings, components, or spaces are connected, arranged, or influence one another.
-
C.
hasDesignRelationship
Indicates that there exists a design-based relationship or association between two entities, such as one influencing, constraining, or deriving from the design of the other.
-
D.
testsRelation
Indicates a relationship where one entity evaluates, examines, or verifies another entity, typically to assess its properties, behavior, or correctness.
-
E.
hasRelationSymbol
Indicates that there exists a specific relational operator or symbol used to denote the relationship between entities.
- F. None of above. chosen
Provenance (4 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291815f88190a6eaf73e444dc1c2 |
completed | April 28, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69e71b20ec50819096ac196c798f8e3c |
completed | April 21, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e7222d208c819098b12c13e31af629 |
completed | April 21, 2026, 7:07 a.m. |
Created at: April 16, 2026, 8:30 p.m.