Triple
T27489659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Healy Power Plant |
E693843
|
entity |
| Predicate | coalSource |
P34519
|
FINISHED |
| Object | Usibelli Coal Mine |
—
|
NE NERFINISHED |
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: Usibelli Coal Mine | Statement: [Healy Power Plant, coalSource, Usibelli Coal Mine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coalSource Context triple: [Healy Power Plant, coalSource, Usibelli Coal Mine]
-
A.
coalMeasure
Indicates that something is a geological coal-bearing stratum or formation within the coal measures sequence.
-
B.
coalMinedFrom
chosen
Indicates that a quantity or batch of coal has been extracted from a particular source location, such as a mine or geological deposit.
-
C.
coalType
Indicates the specific kind or classification of coal associated with an entity.
-
D.
coalTypeMined
Indicates that a particular type of coal is extracted or produced through mining at a given location or by a given agent.
-
E.
fuelSourceForSmelting
Indicates that one entity serves as the fuel used to generate heat for smelting 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e882cbc81908caa3e8a5fb5c1f4 |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:04 p.m.