Triple
T7165931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umananda Temple |
E167066
|
entity |
| Predicate | locatedInWaterBodyType |
P75237
|
FINISHED |
| Object | river island |
—
|
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: river island | Statement: [Umananda Temple, locatedInWaterBodyType, river island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInWaterBodyType Context triple: [Umananda Temple, locatedInWaterBodyType, river island]
-
A.
locatedOnWaterbody
Indicates that an entity is situated on or directly adjacent to a specified body of water.
-
B.
locatedInBodyOfWater
Indicates that an entity is situated within or on the surface of a specific body of water.
-
C.
isInlandWaterBodyOf
Indicates that one water body is an inland (non-oceanic) water feature that is geographically part of, contained within, or associated with another entity.
-
D.
isFreshwaterBody
Indicates that the referenced body of water consists primarily of non-saline (fresh) water rather than saltwater.
-
E.
connectedBodyOfWater
Indicates that two geographic locations are linked by a continuous body of water through which water can flow between them.
- 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_69c68888c10c819095e0383020225758 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e832d2548190aacff0de80dbc268 |
completed | March 27, 2026, 8:27 p.m. |
| PD | Predicate disambiguation | batch_69c6e1cd5c948190a9113b23f7308c21 |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a213508190a40aca39f9eee7d5 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:48 p.m.