Triple
T28942541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mangalesha |
E730489
|
entity |
| Predicate | supportedArchitectureSite |
P203856
|
FINISHED |
| Object | Badami cave temples |
E198054
|
NE 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: Badami cave temples | Statement: [Mangalesha, supportedArchitectureSite, Badami cave temples]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedArchitectureSite Context triple: [Mangalesha, supportedArchitectureSite, Badami cave temples]
-
A.
supportedArchitect
Indicates that one entity provides architectural backing, endorsement, or assistance to another entity or architectural concept.
-
B.
usesArchitecture
Indicates that one entity is built, implemented, or operates according to the architectural style, framework, or design specified by another entity.
-
C.
supportedPlatform
Indicates that one entity (such as a system, application, or service) is compatible with and can operate on a particular platform.
-
D.
laterSupportedArchitecture
Indicates that one architecture provides support for another architecture that was introduced or adopted at a later time.
-
E.
supportedSystem
Indicates that one entity provides compatibility, functionality, or operational support for another system.
- F. None of above. chosen
Provenance (5 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_6a0226c8b2f881909de3c1a5ba40fc49 |
completed | May 11, 2026, 6:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a24ec45d8488190a1b7dd7f28f36add |
completed | June 7, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_6a0225602acc8190978ab4aacc615b8d |
completed | May 11, 2026, 6:52 p.m. |
| PDg | Predicate description generation | batch_6a0226c7f31c819093c2049efccbacbc |
completed | May 11, 2026, 6:58 p.m. |
Created at: April 28, 2026, 8:37 a.m.