Triple
T2501079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bradford |
E52464
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Roubaix |
E223522
|
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: Roubaix | Statement: [Bradford, twinTown, Roubaix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roubaix Context triple: [Bradford, twinTown, Roubaix]
-
A.
Roubaix
chosen
Roubaix is a city in northern France known for its textile industry heritage and as the finish of the Paris–Roubaix professional cycling race.
-
B.
Dauphiné
Dauphiné is a historical region in southeastern France, centered around Grenoble in the Alps, known for its role in French history and distinctive alpine culture.
-
C.
Paris–Lille
Paris–Lille is a major high-speed rail corridor in northern France connecting the capital Paris with the city of Lille.
-
D.
La Flèche Wallonne
La Flèche Wallonne is a prestigious one-day professional road cycling race held annually in Belgium, renowned for its steep, decisive climbs such as the Mur de Huy.
-
E.
Paris–Roubaix
Paris–Roubaix is one of cycling’s oldest and most prestigious one-day “Monument” races, famed for its brutal cobblestone sectors and often unpredictable, harsh conditions.
- 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_69ab4957b3a88190adf968ae0c1b931c |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd1b144a481909b1f8d96742a92e7 |
completed | March 7, 2026, 7:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1fa0e26481908e383a6d44b3f3d5 |
completed | March 9, 2026, 7:29 p.m. |
Created at: March 6, 2026, 9:46 p.m.