Triple
T24496309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Township of Matilda |
E617803
|
entity |
| Predicate | isPartOfHistoricalCounty |
P103366
|
FINISHED |
| Object | Dundas County |
—
|
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: Dundas County | Statement: [Township of Matilda, isPartOfHistoricalCounty, Dundas County]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfHistoricalCounty Context triple: [Township of Matilda, isPartOfHistoricalCounty, Dundas County]
-
A.
historicalCounty
Indicates that an entity was located within or associated with a county as it existed in the past, even if that county’s boundaries or administrative status have since changed.
-
B.
historicCountyPart
chosen
Indicates that one entity forms a constituent part or subdivision of a historic county.
-
C.
hasAssociatedHistoricCounty
Indicates that an entity is linked to a specific historic county with which it is geographically or administratively associated.
-
D.
coversHistoricCounty
Indicates that one entity geographically encompasses the area of a historic county.
-
E.
hasHistoricCountyStatusSince
Indicates that an entity has held the legal or recognized status of a historic county starting from a specified point in time.
- 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_69e2d7f4e6bc8190aec540ae3b9ed7f2 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:22 a.m.