Triple
T34888534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montreal–Quebec City |
E1006216
|
entity |
| Predicate | hasProvinceCapitalAtOneEnd |
P204141
|
FINISHED |
| Object | Quebec City |
E7422
|
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: Quebec City | Statement: [Montreal–Quebec City, hasProvinceCapitalAtOneEnd, Quebec City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProvinceCapitalAtOneEnd Context triple: [Montreal–Quebec City, hasProvinceCapitalAtOneEnd, Quebec City]
-
A.
hasProvincialCapitalWithin
Indicates that a province’s official capital city is geographically located within the boundaries of a specified area or region.
-
B.
connectsToRegionalCapital
Indicates that one location has a direct connection, such as a transport or administrative link, to a designated regional capital.
-
C.
hasCountryCapitalOfProvince
Indicates that a country has a specific city that serves as the capital of one of its provinces.
-
D.
borderProvinceCapitalOf
Indicates that a province shares a land or water boundary with the province in which the specified capital city is located.
-
E.
isInProvinceWithCapital
Indicates that a place is located within a province whose administrative capital is a specified city.
- 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_6a0332a08b48819094aaed6e04a36886 |
completed | May 12, 2026, 2:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3803ec4dc481909c590ea58bbfecbe |
completed | June 21, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_6a0331998a688190b5d919697d4231ac |
completed | May 12, 2026, 1:56 p.m. |
| PDg | Predicate description generation | batch_6a03329fbbb0819099840a6a011eb411 |
completed | May 12, 2026, 2:01 p.m. |
Created at: May 3, 2026, 4 p.m.