Triple
T20458112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish border |
E501848
|
entity |
| Predicate | crossesCounty |
P4247
|
FINISHED |
| Object | Louth |
—
|
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: Louth | Statement: [Irish border, crossesCounty, Louth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louth Context triple: [Irish border, crossesCounty, Louth]
-
A.
Louth
Louth is a historic market town in eastern England known for its Georgian architecture and traditional rural character.
-
B.
Westmeath
Westmeath is a former township in Ontario, Canada, that later became part of the rural municipality known as Whitewater Region.
-
C.
Offaly
Offaly is a largely rural county in Ireland’s Midlands, known for its boglands, historic monastic sites, and the town of Tullamore.
-
D.
County Louth
chosen
County Louth is Ireland’s smallest county by area, located on the east coast and known for its rich early Christian heritage and historic towns such as Drogheda and Dundalk.
-
E.
Fermanagh
Fermanagh is a largely rural historic county in the west of Northern Ireland, noted for its lakelands, especially Lough Erne, and its central town of Enniskillen.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e696a2a8a88190992211b09295d8ea |
completed | April 20, 2026, 9:12 p.m. |
Created at: April 16, 2026, 11:33 a.m.