Triple
T17283948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminus Longueuil |
E419602
|
entity |
| Predicate | isKeyNodeInNetwork |
P20548
|
FINISHED |
| Object | Greater Montreal public transit network |
—
|
LITERAL 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: Greater Montreal public transit network | Statement: [Terminus Longueuil, isKeyNodeInNetwork, Greater Montreal public transit network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isKeyNodeInNetwork Context triple: [Terminus Longueuil, isKeyNodeInNetwork, Greater Montreal public transit network]
-
A.
isKeyNodeIn
chosen
Indicates that a node serves as a primary or critical element within a specified structure, system, or context.
-
B.
isOnNetwork
Indicates that an entity is currently connected to, accessible through, or operating within a specified network.
-
C.
isKeyConnectionPointFor
Indicates that something serves as a primary or critical linking point that connects or integrates other elements within a system or structure.
-
D.
isPartOfNetworkEnd
Indicates that an entity functions as a terminal or boundary component within a larger network structure or system.
-
E.
isInKey
Indicates that something is located within, or belongs to, a specified key or key-based grouping in a structured context.
- F. None of above.
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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4332bd324819080795152293d6d43 |
completed | April 19, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69e3832c3b98819091967ac7e91ba316 |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:40 a.m.