Triple
T8720045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TER Normandie |
E206987
|
entity |
| Predicate | usesRollingStock |
P5426
|
FINISHED |
| Object | SNCF Class Z 55500 |
E767538
|
NE 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: SNCF Class Z 55500 | Statement: [TER Normandie, usesRollingStock, SNCF Class Z 55500]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SNCF Class Z 55500 Context triple: [TER Normandie, usesRollingStock, SNCF Class Z 55500]
-
A.
SNCF Class Z 55500
chosen
The SNCF Class Z 55500 is a modern electric multiple unit train operated by the French national railway company for regional passenger services.
-
B.
SNCF Class Z 51500
The SNCF Class Z 51500 is a type of modern electric multiple unit train operated in regional passenger service across the French railway network.
-
C.
SNCF Class Z 26500
The SNCF Class Z 26500 is a fleet of French double-deck electric multiple unit trains designed for regional passenger services.
-
D.
SNCF Class Z 27500
The SNCF Class Z 27500 is a series of modern electric multiple units operated by the French national railway company for regional passenger services.
-
E.
SNCF Class Z 31500
The SNCF Class Z 31500 is a type of electric multiple unit train operated by the French national railway company for regional passenger services.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca835811d8819081ea00fd2a2c9a1c |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d02a52c81909f93622ae6920b80 |
completed | March 31, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d121cb33188190b5b70020a041c18f |
completed | April 4, 2026, 2:35 p.m. |
Created at: March 30, 2026, 6:36 p.m.