Triple
T36595347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benguela Railway |
E902780
|
entity |
| Predicate | connectsMiningRegion |
P115626
|
FINISHED |
| Object | Katanga |
—
|
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: Katanga | Statement: [Benguela Railway, connectsMiningRegion, Katanga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsMiningRegion Context triple: [Benguela Railway, connectsMiningRegion, Katanga]
-
A.
connectsToMiningRegion
chosen
Indicates a relationship where something is physically or functionally linked to a mining region, such as through infrastructure, operations, or direct access.
-
B.
isMiningRegion
Indicates that a region is characterized by or designated for mining activities or mineral extraction.
-
C.
connectsMine
Indicates that one entity is linked or joined to another entity in the context of a mine or mining-related structure.
-
D.
connectsSettlementRegion
Indicates a relationship where a settlement is linked or associated with a broader geographic region it belongs to or is situated within.
-
E.
connectsRegions
Indicates a relationship where one entity links or joins two or more distinct regions, enabling passage, interaction, or continuity between them.
- 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_69f76e6592e88190bac4eb00a46e9df9 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffb82be8148190a1c870d467a28c80 |
completed | May 9, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69ffb7bbd550819094052e9a0d0ae320 |
completed | May 9, 2026, 10:39 p.m. |
Created at: May 3, 2026, 4:11 p.m.