Triple
T16184895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sahiwal Coal Power Project |
E392774
|
entity |
| Predicate | capacityPerUnit |
P80385
|
FINISHED |
| Object | 660 MW |
—
|
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: 660 MW | Statement: [Sahiwal Coal Power Project, capacityPerUnit, 660 MW]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capacityPerUnit Context triple: [Sahiwal Coal Power Project, capacityPerUnit, 660 MW]
-
A.
unitCapacity
chosen
Indicates the maximum quantity or load that a single unit is designed or allowed to hold, process, or accommodate.
-
B.
capacityPerSide
Indicates the maximum quantity or volume that each individual side or unit in a pair can hold or accommodate.
-
C.
capacityPerHour
Indicates the maximum amount of output or throughput an entity can handle or produce in one hour.
-
D.
capacityCategory
Indicates the classification of something based on the amount or volume it can hold, handle, or accommodate.
-
E.
typicalCapacity
Indicates the usual or standard amount, volume, or capability that something is designed or expected to hold, handle, or perform under normal conditions.
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e22060dcf88190b7c662946a5f0191 |
completed | April 17, 2026, 11:58 a.m. |
| PD | Predicate disambiguation | batch_69e219d642708190ba31a90dce76a210 |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:02 a.m.