Triple
T839075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Degesch |
E18135
|
entity |
| Predicate | productOriginalPurpose |
P11902
|
FINISHED |
| Object | fumigation |
—
|
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: fumigation | Statement: [Degesch, productOriginalPurpose, fumigation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productOriginalPurpose Context triple: [Degesch, productOriginalPurpose, fumigation]
-
A.
primaryProduct
Indicates that one entity is the main or most important product associated with, produced by, or offered by another entity.
-
B.
usedByManufacturer
Indicates that a manufacturer makes use of a particular resource, component, method, or tool in its production or operational processes.
-
C.
usedFor
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
D.
originallyDevelopedFor
chosen
Indicates that something was first created, designed, or produced with the primary purpose of serving a particular use, user group, context, or application.
-
E.
purpose
Indicates that one entity exists, is done, or is used in order to achieve, support, or serve the goal, function, or intended outcome 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_69a49389f44881909a608fb27d89f247 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4abe4ab1081909207ae2eec1898d9 |
completed | March 1, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69a4aa7dfc5c8190890c9df485d73a86 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.