Triple
T12839638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Gare de Lyon |
E307013
|
entity |
| Predicate | hasConnection |
P8776
|
FINISHED |
| Object | TGV services |
E413016
|
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: TGV services | Statement: [Paris Métro Gare de Lyon, hasConnection, TGV services]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TGV services Context triple: [Paris Métro Gare de Lyon, hasConnection, TGV services]
-
A.
TGV services
chosen
TGV services are France’s high-speed train operations, providing fast intercity and international rail connections across the country and beyond.
-
B.
TGV Nord services
TGV Nord services are high-speed train routes in northern France that connect major cities and the Channel Tunnel with Paris and other key destinations.
-
C.
TGV Atlantique services
TGV Atlantique services are high-speed French train operations running primarily between Paris and western or southwestern France using TGV Atlantique trainsets.
-
D.
TGV Réseau
TGV Réseau is a later-generation French high-speed trainset used by SNCF, designed for improved performance and comfort on the expanding TGV network.
-
E.
TGV network
The TGV network is France’s high-speed rail system, linking major cities and neighboring countries with fast, long-distance train 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96ff11b4481909fb2f92c46186853 |
completed | April 10, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68edd30e881909062e8f91f614990 |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:35 p.m.