Triple
T26204981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erythroxylum coca |
E655336
|
entity |
| Predicate | leafUsedFor |
P98
|
FINISHED |
| Object | chewing with lime or ash |
—
|
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: chewing with lime or ash | Statement: [Erythroxylum coca, leafUsedFor, chewing with lime or ash]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leafUsedFor Context triple: [Erythroxylum coca, leafUsedFor, chewing with lime or ash]
-
A.
usedFor
chosen
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
B.
leavesIn
Indicates that one entity departs from or exits another entity, such as a place, group, or state, at a particular time or under certain conditions.
-
C.
leafPresence
Indicates whether leaves are present on an entity (such as a plant or tree) during a given time or condition.
-
D.
usedAt
Indicates that something is employed, applied, or utilized at a particular place, time, or context.
-
E.
partUsed
Indicates that one entity is a component or part that is utilized in the construction, operation, or composition 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60cde512c819094036b09613ff330 |
completed | May 2, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69f5b007ec1c819092e2c3605933f60b |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:50 p.m.