Triple
T25336855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roquefort-sur-Soulzon caves |
E635299
|
entity |
| Predicate | airCirculation |
P41511
|
FINISHED |
| Object | vertical and horizontal through rock fissures |
—
|
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: vertical and horizontal through rock fissures | Statement: [Roquefort-sur-Soulzon caves, airCirculation, vertical and horizontal through rock fissures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airCirculation Context triple: [Roquefort-sur-Soulzon caves, airCirculation, vertical and horizontal through rock fissures]
-
A.
ventilationFeature
chosen
Indicates that one entity has a structural or functional role related to providing, enabling, or affecting ventilation for another entity.
-
B.
controlsVentDistributionOn
Indicates that one entity regulates or directs the distribution of airflow through vents on another entity.
-
C.
airIntakeType
Indicates the type or configuration of the system or mechanism used to draw air into an engine or device.
-
D.
hasFanMovement
Indicates that an entity exhibits or is associated with the motion or operation of a fan.
-
E.
airPurifying
Indicates that an entity removes or reduces pollutants or contaminants from the air in its surroundings.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f498b39adc8190b0fc4925ce0769ed |
completed | May 1, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:32 p.m.