Triple
T19600508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pontygwaith |
E470458
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Porth |
—
|
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: Porth | Statement: [Pontygwaith, hasNearbySettlement, Porth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porth Context triple: [Pontygwaith, hasNearbySettlement, Porth]
-
A.
Porth
chosen
Porth is a town in the Rhondda Valley of South Wales, historically known as a coal mining community and often referred to as the "Gateway to the Rhondda."
-
B.
Green Porth
Green Porth is a small, scenic sandy beach on the island of Tresco in the Isles of Scilly, England.
-
C.
Porthenys
Porthenys is the Cornish-language name for the fishing village of Mousehole in Cornwall, England.
-
D.
Portnahaven
Portnahaven is a small coastal village located on the southwest tip of the Scottish island of Islay, known for its picturesque harbor and views toward the Atlantic.
-
E.
Brean
Brean is a coastal village in Somerset, England, known for its long sandy beach, holiday parks, and proximity to the resort town of Burnham-on-Sea.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6407df98c8190b258ac3b690fe4b1 |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.