Triple
T19017340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Athabasca oil sands |
E465385
|
entity |
| Predicate | inSituTechnology |
P134137
|
FINISHED |
| Object | steam-assisted gravity drainage |
—
|
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: steam-assisted gravity drainage | Statement: [Athabasca oil sands, inSituTechnology, steam-assisted gravity drainage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inSituTechnology Context triple: [Athabasca oil sands, inSituTechnology, steam-assisted gravity drainage]
-
A.
stasisTechnology
Indicates a relationship where an entity uses or involves technology that can halt, slow, or suspend time, motion, or change for objects or beings.
-
B.
drillingSite
Indicates a location where drilling activities are conducted or intended to occur.
-
C.
environmentalTechnology
Indicates a relationship where a technology is designed for, applied to, or primarily concerned with protecting, monitoring, or improving the environment.
-
D.
miningSite
Indicates a location where mining activities or mineral extraction operations take place.
-
E.
subsurfaceSamplingDevice
Indicates a device is used to collect or sample materials from beneath a surface, such as soil, rock, or sediment layers.
- F. None of above. chosen
Provenance (4 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6dc0f9081909cddc5186603e885 |
completed | April 20, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69e4a2fd80c081908237317a3a883e1c |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 12:02 p.m.