Triple
T26854202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tugela Mouth |
E676139
|
entity |
| Predicate | riverEmptiesInto |
P128783
|
FINISHED |
| Object | Indian Ocean |
—
|
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 Ocean | Statement: [Tugela Mouth, riverEmptiesInto, Indian Ocean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverEmptiesInto Context triple: [Tugela Mouth, riverEmptiesInto, Indian Ocean]
-
A.
riverMouthEmptiesInto
chosen
Indicates that the mouth of a river flows into and discharges its water into another body of water, such as a sea, ocean, lake, or another river.
-
B.
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.
-
C.
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.
-
D.
riverMouthAt
Indicates that the mouth or endpoint of a river is located at a specified place or geographic feature.
-
E.
distributaryOf
Indicates that one watercourse branches off from a main river or stream and carries its water away, rather than feeding into it.
- 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_69eee9b9d7708190a15d7485709ae981 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f65aa07c048190a5df30d53d8f0cf5 |
completed | May 2, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f659cc571c819097e51e531961d812 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, 5:19 a.m.