Triple
T22168220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Killyleagh |
E547850
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Comber |
—
|
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: Comber | Statement: [Killyleagh, nearbyTown, Comber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Comber Context triple: [Killyleagh, nearbyTown, Comber]
-
A.
Comber
chosen
Comber is a small town in Northern Ireland known for its historic links to the linen industry and its location near Strangford Lough in County Down.
-
B.
Comber
Comber is a small rural community within the Town of Lakeshore in southwestern Ontario, Canada.
-
C.
Halcombe
Halcombe is a small rural township in New Zealand’s Manawatū-Whanganui region, known for its farming community and historic railway origins.
-
D.
Scawby
Scawby is a rural village and civil parish in North Lincolnshire, England, known for its historic estate and traditional English countryside setting.
-
E.
Humberston
Humberston is a coastal village and civil parish in North East Lincolnshire, England, known for its proximity to the North Sea and the nearby resort of Cleethorpes.
- 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_69e11e3c4c5c81908d336165816b12e0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a6642b08190980fa0c0d2bb4229 |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.