Triple
T2156901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ffestiniog Railway |
E47909
|
entity |
| Predicate | terminus |
P388
|
FINISHED |
| Object | Porthmadog |
E57826
|
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: Porthmadog | Statement: [Ffestiniog Railway, terminus, Porthmadog]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porthmadog Context triple: [Ffestiniog Railway, terminus, Porthmadog]
-
A.
Porthmadog
chosen
Porthmadog is a coastal town in Gwynedd, Wales, known as a gateway to Snowdonia and for its historic harbour and heritage railways.
-
B.
Pwllheli
Pwllheli is a coastal market town and popular seaside resort on the Llŷn Peninsula in Gwynedd, northwest Wales.
-
C.
Porthcawl
Porthcawl is a seaside town in South Wales known for its sandy beaches, promenade, and popular holiday resorts.
-
D.
Barmouth
Barmouth is a seaside town and popular holiday resort on the west coast of Wales, known for its sandy beach and scenic location at the mouth of the Mawddach Estuary.
-
E.
Narberth
Narberth is a small market town in southwest Wales known for its independent shops, arts scene, and historic castle remains.
- 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe67d6888190b8d3c07527c8f80e |
completed | March 7, 2026, 5:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b28d7afe8c81908eda4fd11abcb476 |
completed | March 12, 2026, 9:55 a.m. |
Created at: March 4, 2026, 7:44 p.m.