Triple
T9636818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Rivers |
E232952
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Ballina |
E264989
|
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: Ballina | Statement: [Northern Rivers, hasTown, Ballina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ballina Context triple: [Northern Rivers, hasTown, Ballina]
-
A.
Ballina
chosen
Ballina is a coastal town in northern New South Wales, Australia, known for its beaches, riverfront, and role as a regional service and tourism hub.
-
B.
Ballina
Ballina is a prominent town in County Mayo in Ireland, known for its location along the River Moy and its strong fishing and cultural heritage.
-
C.
Enniscrone
Enniscrone is a coastal resort town in County Sligo, Ireland, known for its long sandy beach, surfing, and seaside tourism.
-
D.
Bagenalstown
Bagenalstown is a small market town in County Carlow, Ireland, situated on the River Barrow and known for its historic architecture and canal-side setting.
-
E.
Ballyhaunis
Ballyhaunis is a small market town in east County Mayo, Ireland, known as a local commercial and transport hub with a diverse community.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b5045cc8190ab717f42d803e010 |
completed | April 1, 2026, 10:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1823e32c48190a442b77a0f7c8180 |
completed | April 4, 2026, 9:27 p.m. |
Created at: March 30, 2026, 8:11 p.m.