Triple
T128761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montreal |
E2604
|
entity |
| Predicate | hasMetroSystem |
P522
|
FINISHED |
| Object | Montreal Metro |
E13868
|
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: Montreal Metro | Statement: [Montreal, hasMetroSystem, Montreal Metro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Montreal Metro Context triple: [Montreal, hasMetroSystem, Montreal Metro]
-
A.
Orlyval
Orlyval is an automated light rail shuttle service in the Paris region that links Orly Airport to the broader RER and metro network.
-
B.
RER B line
The RER B line is a major Paris regional express railway line that connects central Paris with key northern and southern suburbs, including Charles de Gaulle Airport.
-
C.
Société de transport de Montréal
chosen
The Société de transport de Montréal is the public transit authority responsible for operating Montreal’s bus and metro networks.
-
D.
Toronto Transit Commission
The Toronto Transit Commission is the public agency that operates Toronto’s primary network of subways, buses, and streetcars.
-
E.
Portland Streetcar
Portland Streetcar is a modern urban streetcar transit system serving central Portland, Oregon, connecting key neighborhoods, employment centers, and educational institutions.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a2576518e0819096b35d8af7a4d1bd |
completed | Feb. 28, 2026, 2:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2aa453a8c81908d6d4d14aff8522e |
completed | Feb. 28, 2026, 8:41 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.