Triple
T2485259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saldanha Bay |
E55910
|
entity |
| Predicate | geographicFeatureType |
P9677
|
FINISHED |
| Object | coastal bay |
—
|
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: coastal bay | Statement: [Saldanha Bay, geographicFeatureType, coastal bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicFeatureType Context triple: [Saldanha Bay, geographicFeatureType, coastal bay]
-
A.
GNISFeatureClass
chosen
Indicates the categorical type or class assigned to a geographic feature in the Geographic Names Information System (GNIS).
-
B.
politicalFeature
Indicates that an entity possesses a political characteristic, attribute, or aspect relevant to governance, power structures, or public policy.
-
C.
terrainFeature
Indicates a relationship where one entity is a natural or constructed landform or surface characteristic associated with a given location or area.
-
D.
riverFeatureType
Indicates the specific kind or category of physical or functional feature associated with a river (e.g., source, mouth, tributary, channel segment).
-
E.
typeOfToponym
Indicates the specific category or kind of place name (toponym) that applies to a given geographic entity.
- 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_69ab49e670a88190b928e08302381710 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd20b6d008190acec0eb172e218c9 |
completed | March 7, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69abd0b7cf088190bcff4dac6150044c |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:45 p.m.