Triple
T25042246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Global Commerce division |
E627142
|
entity |
| Predicate | worksForBenefitOf |
P77057
|
FINISHED |
| Object | communities in Georgia |
—
|
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: communities in Georgia | Statement: [Global Commerce division, worksForBenefitOf, communities in Georgia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksForBenefitOf Context triple: [Global Commerce division, worksForBenefitOf, communities in Georgia]
-
A.
benefice
chosen
Indicates that one entity grants or bestows a benefit, favor, or advantage upon another.
-
B.
worksAgainst
Indicates that one entity actively opposes, counteracts, or undermines the goals, effects, or interests of another entity.
-
C.
worksWellFor
Indicates that something is effective, suitable, or produces good results for a particular entity, context, or purpose.
-
D.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
-
E.
workFor
Indicates that one entity is employed by or performs work under the authority or direction of 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_69e2ff2b4c80819087c916b2b16241b9 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f4530c59688190a7006c6948cc7073 |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d77f6e88190a4643ab2cbef567b |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:08 a.m.