Triple
T10959811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabica |
E258939
|
entity |
| Predicate | globalMarketShare |
P90779
|
FINISHED |
| Object | about 60 percent of world coffee production |
—
|
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: about 60 percent of world coffee production | Statement: [Arabica, globalMarketShare, about 60 percent of world coffee production]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: globalMarketShare Context triple: [Arabica, globalMarketShare, about 60 percent of world coffee production]
-
A.
peakMarketShare
Indicates the highest proportion of total market sales or customers that an entity has achieved over a specified period.
-
B.
marketShareUS
Indicates the proportion of a product, company, or brand’s total sales or volume within the United States market relative to the overall U.S. market size.
-
C.
hasGlobalMarketShare
chosen
Indicates that an entity possesses a specified proportion of sales or presence in the worldwide market relative to all competitors.
-
D.
marketSize
Indicates the total volume or value of demand for a product, service, or market segment within a defined scope (such as a time period or geographic region).
-
E.
mediaMarket
Indicates a relationship where a media outlet or content provider serves, targets, or operates within a particular geographic or demographic market.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77127b10481908ad1efafb2a338d1 |
completed | April 9, 2026, 9:28 a.m. |
| PD | Predicate disambiguation | batch_69d72e874f48819096ffa878f90c7d5b |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.