Triple
T25480794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walvis Bay Corridor Group |
E638566
|
entity |
| Predicate | linksToMarket |
P89717
|
FINISHED |
| Object | South Africa |
—
|
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: South Africa | Statement: [Walvis Bay Corridor Group, linksToMarket, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linksToMarket Context triple: [Walvis Bay Corridor Group, linksToMarket, South Africa]
-
A.
relatedMarket
Indicates that two markets are connected or associated, such that activity, conditions, or changes in one market are relevant to or influence the other.
-
B.
marketsAs
Indicates that one entity promotes, advertises, or sells another entity as a product, service, or offering in the marketplace.
-
C.
marketsIn
Indicates that one entity promotes, sells, or offers another entity’s products or services within a particular market or geographic area.
-
D.
coversMarket
chosen
Indicates that one entity operates in, serves, or has business presence within a particular market or geographic/sectoral area.
-
E.
marketsThrough
Indicates that one entity promotes, sells, or distributes its products or services by using another entity as a marketing or sales channel.
- 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_69f5f77658dc8190975f60eb762b25d5 |
completed | May 2, 2026, 1:09 p.m. |
| PD | Predicate disambiguation | batch_69f5afd5baac8190bb8ed576813c8591 |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 2:31 p.m.