Triple
T36890676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lakkundi |
E911736
|
entity |
| Predicate | waterArchitecture |
P20923
|
FINISHED |
| Object | ornate stepped wells |
—
|
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: ornate stepped wells | Statement: [Lakkundi, waterArchitecture, ornate stepped wells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterArchitecture Context triple: [Lakkundi, waterArchitecture, ornate stepped wells]
-
A.
waterInfrastructure
Indicates the existence, development, or management of systems and facilities that supply, store, treat, or distribute water between entities.
-
B.
waterFeature
chosen
Indicates the presence of a natural or artificial body or flow of water associated with the subject.
-
C.
constructedWaterway
Indicates a water channel or route that has been artificially created or significantly modified by human construction.
-
D.
waterDepiction
Indicates that one entity visually represents or portrays water in some form (e.g., as a subject, element, or feature) in an image or depiction.
-
E.
floodResistanceDesign
Indicates that something is designed or engineered to withstand, mitigate, or remain functional during flooding conditions.
- 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_69f76e8335908190b77e7e11d0e80820 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe30bc64308190b603ff1b30c2aeee |
completed | May 8, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69fe2f7175b081908dd61e1513620bbe |
completed | May 8, 2026, 6:46 p.m. |
Created at: May 3, 2026, 4:13 p.m.