Triple
T12384649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanzania and Zambia |
E295831
|
entity |
| Predicate | borderIncludes |
P57389
|
FINISHED |
| Object | shoreline of Lake Tanganyika |
—
|
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: shoreline of Lake Tanganyika | Statement: [Tanzania and Zambia, borderIncludes, shoreline of Lake Tanganyika]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderIncludes Context triple: [Tanzania and Zambia, borderIncludes, shoreline of Lake Tanganyika]
-
A.
borderRegionsInclude
chosen
Indicates that the specified border area encompasses or contains the referenced regions within its boundaries.
-
B.
borderIsAffectedBy
Indicates that a border’s state, condition, or characteristics are influenced or changed by another factor or event.
-
C.
borderDefinedBy
Indicates that the boundary or limit of one entity is determined, shaped, or delineated by another entity.
-
D.
borderRegion
Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
-
E.
borderStraddling
Indicates that something (such as a feature, structure, or area) extends across and occupies territory on both sides of a border between two regions or jurisdictions.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbc3f608190b0ee3c4f304a94db |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.