Triple
T23851968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinatown, Ottawa |
E592193
|
entity |
| Predicate | gatewayType |
P104475
|
FINISHED |
| Object | paifang-style arch |
—
|
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: paifang-style arch | Statement: [Chinatown, Ottawa, gatewayType, paifang-style arch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gatewayType Context triple: [Chinatown, Ottawa, gatewayType, paifang-style arch]
-
A.
gateType
Indicates the specific kind or classification of a gate associated with an entity.
-
B.
hasGatewayType
chosen
Indicates that an entity is associated with or configured to use a specific type or category of gateway.
-
C.
gateWeight
Indicates the weight or importance assigned to a particular gate or transition within a process, model, or system.
-
D.
gangwayType
Indicates the specific kind or configuration of gangway used to provide passage between areas or vehicles.
-
E.
servesAsGatewayTo
Indicates that one entity functions as an entry point, access route, or intermediary channel that enables reaching or connecting to another entity.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c987c3208190bf3f210d12106927 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:11 p.m.