Triple
T15928507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyon tram line T2 |
E386264
|
entity |
| Predicate | hasStop |
P17789
|
FINISHED |
| Object | Perrache |
E79034
|
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: Perrache | Statement: [Lyon tram line T2, hasStop, Perrache]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perrache Context triple: [Lyon tram line T2, hasStop, Perrache]
-
A.
Perrache quarter
The Perrache quarter is a historic district in Lyon, France, known for its major railway station, transport hub, and mix of industrial, commercial, and residential areas at the southern end of the Presqu’île.
-
B.
Gare de Vaise
Gare de Vaise is a major transport hub and metro terminus in Lyon, France, serving the northwestern part of the city.
-
C.
Fourvière station
Fourvière station is a funicular railway terminus in Lyon, France, serving the historic Fourvière hill and its basilica.
-
D.
Rambouillet station
Rambouillet station is a railway station in Rambouillet, France, serving as a regional commuter and intercity stop southwest of Paris.
-
E.
Lyon-Perrache station
chosen
Lyon-Perrache station is one of Lyon’s main railway hubs, serving regional, national, and international train connections in southeastern France.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156a39abc8190927818f6e185033a |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe727c348190907c9e7a5db6031d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.