Triple
T23974292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melbourne Causeway |
E604318
|
entity |
| Predicate | hasBodyOfWaterBelow |
P139261
|
FINISHED |
| Object | Indian River |
—
|
NE NERFINISHED |
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: Indian River | Statement: [Melbourne Causeway, hasBodyOfWaterBelow, Indian River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBodyOfWaterBelow Context triple: [Melbourne Causeway, hasBodyOfWaterBelow, Indian River]
-
A.
hasBodyOfWaterType
Indicates that a body of water is classified as being of a particular type or category (such as lake, river, ocean, etc.).
-
B.
hasWaterBodyOnSouth
Indicates that a place or region is bordered or adjacent to a body of water on its southern side.
-
C.
hasRiverBelow
chosen
Indicates that one entity is located above another such that a river lies physically below it.
-
D.
hasWatersOf
Indicates that a geographic or physical entity contains, is traversed by, or is otherwise characterized by specific bodies or types of water.
-
E.
hasBodyOfWaterDrainedBy
Indicates that a body of water is emptied or its water flow is carried away by a specified draining feature, such as a river, channel, or drainage system.
- 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_69e29543f40c819087700b7a272afb60 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d1de6ee081908590e438012e96bd |
completed | April 29, 2026, 9:39 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:26 p.m.