Triple
T10549373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moscow Metro 81-776 series |
E248904
|
entity |
| Predicate | powerCollectionVoltage |
P44291
|
FINISHED |
| Object | 825 V DC |
—
|
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: 825 V DC | Statement: [Moscow Metro 81-776 series, powerCollectionVoltage, 825 V DC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerCollectionVoltage Context triple: [Moscow Metro 81-776 series, powerCollectionVoltage, 825 V DC]
-
A.
supplyVoltageType
chosen
Indicates the type or category of supply voltage associated with or required by an entity.
-
B.
typicalVoltagePerCell
Indicates the standard or commonly expected voltage value associated with each individual cell in a multi-cell system or device.
-
C.
gridVoltageLevel
Indicates the electrical voltage level at which a power grid or network segment operates.
-
D.
maxVoltage
Indicates the maximum electrical potential (voltage) that an entity can safely or normally handle, provide, or operate at.
-
E.
electricalPower
Indicates that one entity supplies, carries, or is associated with electrical power to or for 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d52710869c81909b6db1a190825bad |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d518fa0b4081909bffc936d78bd77b |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:33 p.m.