Triple
T37154347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riverdale, Toronto |
E920451
|
entity |
| Predicate | partOfMunicipalWard |
P76280
|
FINISHED |
| Object | Toronto–Danforth |
—
|
NE NERFINISHED |
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: Toronto–Danforth | Statement: [Riverdale, Toronto, partOfMunicipalWard, Toronto–Danforth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfMunicipalWard Context triple: [Riverdale, Toronto, partOfMunicipalWard, Toronto–Danforth]
-
A.
locatedInCityWard
chosen
Indicates that one entity is situated within the administrative boundaries of a specific city ward.
-
B.
municipalWardType
Indicates the specific category or classification of a municipal ward within a local government or administrative structure.
-
C.
partOfMunicipalCorporation
Indicates that an entity is administratively included within, and governed as a subdivision of, a specific municipal corporation.
-
D.
partOfPrefecturalDistrict
Indicates that one administrative or geographic entity is contained within, and belongs to, a specific prefectural district.
-
E.
partOfSubdistrict
Indicates that one entity is a component or subdivision within a specific subdistrict.
- 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a014a0b57dc8190b04ce51156ab95fa |
completed | May 11, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_6a0149afa57c8190a83257085766d916 |
completed | May 11, 2026, 3:14 a.m. |
Created at: May 3, 2026, 4:15 p.m.