Triple
T16102300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parc Jean-Drapeau |
E390651
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Casino de Montréal |
E429584
|
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: Casino de Montréal | Statement: [Parc Jean-Drapeau, hasPart, Casino de Montréal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Casino de Montréal Context triple: [Parc Jean-Drapeau, hasPart, Casino de Montréal]
-
A.
Montreal Casino
chosen
Montreal Casino is a major gambling and entertainment complex in Montreal, Quebec, known as one of Canada’s largest and most prominent casinos.
-
B.
Casino de la Forêt
Casino de la Forêt is a historic gambling and entertainment venue located in the seaside resort town of Le Touquet-Paris-Plage in northern France.
-
C.
Casino de Paris
Casino de Paris is a historic and iconic Parisian music hall and cabaret venue renowned for its variety shows and star performances.
-
D.
Casino de Beaulieu-sur-Mer
Casino de Beaulieu-sur-Mer is an elegant seaside casino and entertainment venue on the French Riviera, known for its Belle Époque architecture and upscale gaming atmosphere.
-
E.
Normandie Casino
Normandie Casino is a long-standing card club and gambling venue located in Gardena, California.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6976ec8190b499e99b196b0285 |
completed | April 17, 2026, 9:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeba007c08190bf4d3cf092abc7dd |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 5 a.m.