Triple
T8826987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | night trains Paris–Nice |
E210039
|
entity |
| Predicate | endPoint |
P390
|
FINISHED |
| Object | Nice |
E2387
|
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: Nice | Statement: [night trains Paris–Nice, endPoint, Nice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nice Context triple: [night trains Paris–Nice, endPoint, Nice]
-
A.
Nice
Nice is a cabin class offered by Breeze Airways that provides a standard, budget-friendly economy experience for passengers.
-
B.
Nice
chosen
Nice is a prominent Mediterranean coastal city on the French Riviera, known for its mild climate, beaches, and vibrant cultural life.
-
C.
Nice Agreement
The Nice Agreement is an international treaty that establishes a standardized classification system of goods and services used for the registration of trademarks.
-
D.
NICE
NICE is the United Kingdom’s national body that develops evidence-based guidance and standards to improve health and social care.
-
E.
Lovely
"Lovely" is a haunting, melancholic pop ballad by Billie Eilish and Khalid that gained widespread acclaim for its emotional depth and atmospheric production.
- 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_69ca8365b28081909e48e45e95dfc405 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc6034e8dc819099116d772e87569a |
completed | April 1, 2026, midnight |
| NED1 | Entity disambiguation (via context triple) | batch_69cf895a766c81908f41e369afb05023 |
completed | April 3, 2026, 9:33 a.m. |
Created at: March 30, 2026, 6:46 p.m.