Triple
T31008444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SNCF Class ZGC |
E790138
|
entity |
| Predicate | powerCollectionDevice |
P14641
|
FINISHED |
| Object | pantograph |
—
|
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: pantograph | Statement: [SNCF Class ZGC, powerCollectionDevice, pantograph]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerCollectionDevice Context triple: [SNCF Class ZGC, powerCollectionDevice, pantograph]
-
A.
hasPowerCollection
Indicates that one entity possesses or is associated with a collection or set of power-related attributes, capabilities, or resources of another entity.
-
B.
powerCollectionMethod
chosen
Indicates the method or process by which power is collected, harvested, or obtained in a given context.
-
C.
powerInterface
Indicates that one entity serves as a power-providing interface or connection point for another entity, enabling the transfer or supply of electrical power.
-
D.
powering
Indicates that one entity supplies energy or power that enables another entity to operate or function.
-
E.
powerPack
Indicates that one entity serves as a power pack or portable power source 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_69f224c73ca48190a1e46cb58ad4045b |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7465687bc8190a9da44d62b634ed7 |
completed | May 3, 2026, 12:57 p.m. |
| PD | Predicate disambiguation | batch_69f743f4ceb08190a21fe7f4a99b166b |
completed | May 3, 2026, 12:47 p.m. |
Created at: April 29, 2026, 8:57 p.m.