Triple
T18412267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mid Ulster |
E441787
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Cookstown |
—
|
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: Cookstown | Statement: [Mid Ulster, containsTown, Cookstown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cookstown Context triple: [Mid Ulster, containsTown, Cookstown]
-
A.
Cookstown
chosen
Cookstown is a market town in County Tyrone, Northern Ireland, known historically for its long main street and role as a local commercial center.
-
B.
Collinstown
Collinstown is a suburban area in north County Dublin, Ireland, best known today as the locality encompassing Dublin Airport.
-
C.
Edgeworthstown
Edgeworthstown is a small town in County Longford, Ireland, historically associated with the Anglo-Irish Edgeworth family and writer Maria Edgeworth.
-
D.
Carrickmacross
Carrickmacross is a market town in County Monaghan, Ireland, known for its traditional lace-making and historic architecture.
-
E.
Navan
Navan is a town in County Meath, Ireland, known historically as a market and mining center and now a growing commuter hub for Dublin.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a24e130819082b92f98d8d5fa3c |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 10:47 a.m.