Triple
T16570820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TGV Lyria |
E402577
|
entity |
| Predicate | primaryRoute |
P6298
|
FINISHED |
| Object |
Paris–Geneva
Paris–Geneva is a major international high-speed rail route linking the French capital with the Swiss city of Geneva.
|
E1221293
|
NE FINISHED |
How this triple was built (4 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: Paris–Geneva | Statement: [TGV Lyria, primaryRoute, Paris–Geneva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paris–Geneva Context triple: [TGV Lyria, primaryRoute, Paris–Geneva]
-
A.
Paris–Basel
Paris–Basel is an international air route linking the French capital Paris with the Swiss city of Basel.
-
B.
Geneva
Geneva is a major Swiss city on Lake Geneva known for hosting numerous international organizations, including United Nations agencies and the Red Cross.
-
C.
Geneva
Geneva is a small city in northeastern Ohio situated along Lake Erie, known for its wineries, tourism, and location within the Rust Belt region.
-
D.
Geneva
Geneva is a small city in New York's Finger Lakes region, known for its lakeside setting on Seneca Lake and its historic colleges and wineries.
-
E.
Lausanne
Lausanne is a major Swiss city on the shores of Lake Geneva, known for hosting the International Olympic Committee and its vibrant cultural and academic institutions.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Paris–Geneva Triple: [TGV Lyria, primaryRoute, Paris–Geneva]
Generated description
Paris–Geneva is a major international high-speed rail route linking the French capital with the Swiss city of Geneva.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paris–Geneva Target entity description: Paris–Geneva is a major international high-speed rail route linking the French capital with the Swiss city of Geneva.
-
A.
Paris–Basel
Paris–Basel is an international air route linking the French capital Paris with the Swiss city of Basel.
-
B.
Geneva
Geneva is a major Swiss city on Lake Geneva known for hosting numerous international organizations, including United Nations agencies and the Red Cross.
-
C.
Geneva
Geneva is a small city in northeastern Ohio situated along Lake Erie, known for its wineries, tourism, and location within the Rust Belt region.
-
D.
Geneva
Geneva is a small city in New York's Finger Lakes region, known for its lakeside setting on Seneca Lake and its historic colleges and wineries.
-
E.
Lausanne
Lausanne is a major Swiss city on the shores of Lake Geneva, known for hosting the International Olympic Committee and its vibrant cultural and academic institutions.
- F. None of above. chosen
Provenance (5 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_69d8838648088190acf97ef11fc3f61b |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35958d49c8190b995188240fb355b |
completed | April 18, 2026, 10:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ee8812c81908ef74636bf39d44a |
completed | May 10, 2026, 11:41 a.m. |
| NEDg | Description generation | batch_6a0070024cb4819092ee0ce1320f0905 |
completed | May 10, 2026, 11:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00707959a081909fc04947624abbe5 |
completed | May 10, 2026, 11:48 a.m. |
Created at: April 10, 2026, 5:16 a.m.