Triple
T37937543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa–Namibia–Atlantic Ocean point |
E946387
|
entity |
| Predicate | oceanAtPoint |
P87249
|
FINISHED |
| Object | Atlantic 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: Atlantic Ocean | Statement: [South Africa–Namibia–Atlantic Ocean point, oceanAtPoint, Atlantic Ocean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oceanAtPoint Context triple: [South Africa–Namibia–Atlantic Ocean point, oceanAtPoint, Atlantic Ocean]
-
A.
oceanLocation
Indicates that one entity is geographically located in, on, or adjacent to a particular ocean.
-
B.
oceanPresence
chosen
Indicates that an entity is located in, adjacent to, or significantly influenced by an ocean.
-
C.
hasNearbyMarineFeature
Indicates that one entity is located close to a marine geographic feature associated with the other entity.
-
D.
positionRelativeToSurfaceCurrents
Indicates the spatial relationship of an entity’s location or movement with respect to the direction and pattern of surface currents.
-
E.
nearestMainlandPoint
Indicates the relationship where a location is associated with the closest point on the mainland to that location.
- 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_69f76ef531ac8190ae6d99e5786e76ec |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc7b78f9481909f4f8fc2e3fdcde1 |
completed | May 6, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69fbbd18c9908190928d274f8731dfa8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.