Triple
T34888535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montreal–Quebec City |
E1006216
|
entity |
| Predicate | hasProvinceLargestCityAtOneEnd |
P204147
|
FINISHED |
| Object | Montreal |
E2604
|
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 | Statement: [Montreal–Quebec City, hasProvinceLargestCityAtOneEnd, Montreal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProvinceLargestCityAtOneEnd Context triple: [Montreal–Quebec City, hasProvinceLargestCityAtOneEnd, Montreal]
-
A.
hasProvinceCapitalAtOneEnd
Indicates that one end of something (such as a route, boundary, or connection) is located at the capital city of a province.
-
B.
largestCityPartiallyIn
Indicates that one entity is the largest city that lies at least partly within the boundaries of another entity.
-
C.
isProvincialCityOf
Indicates that a city serves as an administrative or officially designated city within a specified province.
-
D.
hasProvincialCapitalWithin
Indicates that a province’s official capital city is geographically located within the boundaries of a specified area or region.
-
E.
governsRegionWithLargestCity
Indicates that a governing entity has authority over the region that contains the largest city in a specified area or jurisdiction.
- F. None of above. chosen
Provenance (5 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_69f76dbedb288190afe5780710847410 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a03352bb9688190b965d188769fcacd |
completed | May 12, 2026, 2:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a380f8b68f48190a1bbc2b51f202dcf |
completed | June 21, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_6a033329ae5c81909532843fe716ec77 |
completed | May 12, 2026, 2:03 p.m. |
| PDg | Predicate description generation | batch_6a03352af3f881909f13f586214027ac |
completed | May 12, 2026, 2:11 p.m. |
Created at: May 3, 2026, 4 p.m.