Triple
T6997969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roquefort |
E162264
|
entity |
| Predicate | airflowSource |
P17870
|
FINISHED |
| Object | fleurines (natural cave vents) |
—
|
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: fleurines (natural cave vents) | Statement: [Roquefort, airflowSource, fleurines (natural cave vents)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airflowSource Context triple: [Roquefort, airflowSource, fleurines (natural cave vents)]
-
A.
deploymentSource
Indicates the origin or mechanism from which something is deployed, such as the system, process, or source responsible for initiating the deployment.
-
B.
dataFlowDirection
Indicates the direction in which data moves or is transmitted from a source entity to a target entity.
-
C.
carbonSource
Indicates that one entity serves as the source or provider of carbon for another entity or process.
-
D.
airframer
Indicates a relationship where a company designs, manufactures, or assembles aircraft as its primary aerospace activity.
-
E.
flowsFrom
chosen
Indicates that a substance, medium, or influence moves or originates from one entity or location and proceeds outward to another.
- 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_69c68857ffc08190857dc62cd5253777 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dbeef57881909245c8a5374a8111 |
completed | March 27, 2026, 7:35 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c67c94819084fdcf0398606027 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:33 p.m.