Triple
T12557446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upminster Depot |
E295253
|
entity |
| Predicate | hasMaintenanceCapability |
P90358
|
FINISHED |
| Object | rolling stock overhaul |
—
|
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: rolling stock overhaul | Statement: [Upminster Depot, hasMaintenanceCapability, rolling stock overhaul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaintenanceCapability Context triple: [Upminster Depot, hasMaintenanceCapability, rolling stock overhaul]
-
A.
hasMaintenance
Indicates that an entity is subject to, associated with, or requires a particular maintenance activity or maintenance record.
-
B.
hasMaintenanceBase
Indicates that an entity is supported, serviced, or maintained at a specific base or maintenance facility.
-
C.
canMaintain
chosen
Indicates that one entity has the ability or capacity to maintain, service, or keep another entity in proper working condition.
-
D.
hasMaintenanceService
Indicates that an entity receives or is covered by a maintenance service provided by another entity.
-
E.
hasMaintenancePort
Indicates that an entity is equipped with a dedicated port or interface used specifically for maintenance, diagnostics, or service operations.
- 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_69d6ad9cac2c81908e8a7bed82d1e21d |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95f5507b481908d13cc317b7402f6 |
completed | April 10, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69d95410d0b0819097646edd1b837104 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 8, 2026, 11:47 p.m.