Triple
T13812342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charonne workshop |
E331923
|
entity |
| Predicate | maintenanceFor |
P26299
|
FINISHED |
| Object | trains operating on Paris Métro Line 2 |
—
|
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: trains operating on Paris Métro Line 2 | Statement: [Charonne workshop, maintenanceFor, trains operating on Paris Métro Line 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintenanceFor Context triple: [Charonne workshop, maintenanceFor, trains operating on Paris Métro Line 2]
-
A.
maintenance
Indicates that an entity performs, requires, or is involved in upkeep, repair, or preservation activities for another entity or system.
-
B.
maintenancePractice
Indicates the specific actions or methods used to preserve, repair, or optimize the condition or performance of something over time.
-
C.
hasMaintenance
Indicates that an entity is subject to, associated with, or requires a particular maintenance activity or maintenance record.
-
D.
maintenanceFeature
Indicates that one entity serves as a maintenance-related feature, capability, or component associated with another entity.
-
E.
maintenanceAuthority
chosen
Indicates that one entity has the responsibility or official power to maintain, service, or keep another entity in proper working condition.
- 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_69d81c59f8808190a851bc56afdc55e9 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de027198f8819095da3e714ac241f5 |
completed | April 14, 2026, 9:01 a.m. |
| PD | Predicate disambiguation | batch_69dbc862e9608190bd8a3d883959b7e4 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:12 p.m.