Triple
T8724743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SNCF Voyageurs |
E207101
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object | Thalys International |
E38855
|
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: Thalys International | Statement: [SNCF Voyageurs, subsidiary, Thalys International]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thalys International Context triple: [SNCF Voyageurs, subsidiary, Thalys International]
-
A.
Thalys
chosen
Thalys is a high-speed international train service connecting major cities in France, Belgium, the Netherlands, and Germany.
-
B.
Eurostar
Eurostar is a high-speed international train service connecting the United Kingdom with mainland Europe via the Channel Tunnel, linking cities such as London, Paris, and Brussels.
-
C.
TGV Lyria
TGV Lyria is a high-speed train service linking France and Switzerland, operated as a joint venture between SNCF and Swiss Federal Railways.
-
D.
Infrabel
Infrabel is the Belgian railway infrastructure manager responsible for the construction, maintenance, and operation of the national rail network.
-
E.
Francorail
Francorail was a French railway manufacturing consortium known for producing high-speed trainsets, including early models of the TGV.
- 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_69cc5d1404948190bc45d14a1ddb1a7e |
completed | March 31, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf88cf76888190a0cdab7f30c791c7 |
completed | April 3, 2026, 9:30 a.m. |
Created at: March 30, 2026, 6:36 p.m.