Triple
T25480788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walvis Bay Corridor Group |
E638566
|
entity |
| Predicate | focusesOnCorridor |
P162102
|
FINISHED |
| Object | Trans-Kalahari Corridor |
—
|
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: Trans-Kalahari Corridor | Statement: [Walvis Bay Corridor Group, focusesOnCorridor, Trans-Kalahari Corridor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnCorridor Context triple: [Walvis Bay Corridor Group, focusesOnCorridor, Trans-Kalahari Corridor]
-
A.
focusesOnCorridor
chosen
Indicates that an action, attention, or process is directed specifically toward a corridor or passageway.
-
B.
followedCorridor
Indicates that an entity moved along and stayed within the path of a corridor from one point to another.
-
C.
corridorFunction
Indicates that one entity serves as a corridor or passageway functionally connecting or providing access between other spaces or areas.
-
D.
inCorridor
Indicates that one entity is located within or inside a corridor relative to another spatial context or reference.
-
E.
hasCorridor
Indicates that one entity includes, is connected by, or provides access through a corridor to another 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_69e75dbabeac8190bab30628f8b799d4 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f627aedf548190bc9f53c8a2d67b50 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 21, 2026, 2:31 p.m.