Triple
T28685353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhavani |
E729115
|
entity |
| Predicate | hasRiverConfluenceType |
P11843
|
FINISHED |
| Object | sangam |
—
|
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: sangam | Statement: [Bhavani, hasRiverConfluenceType, sangam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRiverConfluenceType Context triple: [Bhavani, hasRiverConfluenceType, sangam]
-
A.
riverConfluence
chosen
Indicates the location or relationship where two or more rivers or streams join and merge into a single watercourse.
-
B.
isWatercourseOf
Indicates that a watercourse (such as a river or stream) flows through, belongs to, or is geographically associated with a particular area or feature.
-
C.
isMajorWatercourseOf
Indicates that a watercourse is a primary or significant river or stream associated with, or flowing through, a particular geographic area or feature.
-
D.
isHeadwaterTributaryOf
Indicates that one watercourse is a source or upstream tributary that feeds into another watercourse.
-
E.
hasTributaryRelationWith
Indicates that one entity maintains a tributary relationship with another, typically involving the payment of tribute or acknowledgment of subordinate status.
- 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_69f043e60b6c8190ac2cd042e77fe6e9 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 28, 2026, 5:31 a.m.