Triple
T18608723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rugeley power station A |
E454826
|
entity |
| Predicate | ashDisposal |
P132770
|
FINISHED |
| Object | ash lagoons |
—
|
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: ash lagoons | Statement: [Rugeley power station A, ashDisposal, ash lagoons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ashDisposal Context triple: [Rugeley power station A, ashDisposal, ash lagoons]
-
A.
assetDisposition
Indicates the manner or outcome by which an asset is transferred, retired, sold, or otherwise removed from ownership or active use.
-
B.
disposability
Indicates that one entity can be discarded, replaced, or treated as expendable in relation to another entity or context.
-
C.
drop
Indicates that an entity causes something to fall or be released from a higher position to a lower one.
-
D.
ashFall
Indicates that ash is falling or being deposited from the air onto a location or object.
-
E.
dissipatedOn
Indicates that something (such as energy, force, or a substance) is dispersed, lost, or converted into a less usable form on or within a particular medium, surface, or system.
- 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54cff3be8819080ab20045bd18a4d |
completed | April 19, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69e478cf5e888190a0b1074b0c6525df |
completed | April 19, 2026, 6:40 a.m. |
| PDg | Predicate description generation | batch_69e484121cd48190bf583b4c94636a30 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 11:45 a.m.