Triple
T2908354
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dyfed |
E63619
|
entity |
| Predicate | hasNotableTown |
P14082
|
FINISHED |
| Object | Cardigan |
E139887
|
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: Cardigan | Statement: [Dyfed, hasNotableTown, Cardigan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cardigan Context triple: [Dyfed, hasNotableTown, Cardigan]
-
A.
Cardigan
chosen
Cardigan is a historic coastal town in west Wales known for its medieval castle, riverside setting on the Teifi, and role as a cultural and market center for the surrounding region.
-
B.
Pembroke
Pembroke is a suburban town in southeastern Massachusetts known for its residential character, ponds, and historic New England charm.
-
C.
Pembroke
Pembroke is a historic town in southwest Wales best known as the birthplace of King Henry VII of England and for its prominent medieval castle.
-
D.
Raglan
Raglan is a historic village in southeast Wales best known for the impressive late medieval Raglan Castle.
-
E.
Kersey
Kersey is a historic village in Suffolk, England, noted for its picturesque medieval buildings and traditional rural character.
- 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_69ab4c44ab448190b9411324e8a1fc1d |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe0d1dcf881909b3ae58d7cdfd9cd |
completed | March 7, 2026, 8:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b056173a988190be02619d909cdb25 |
completed | March 10, 2026, 5:34 p.m. |
Created at: March 6, 2026, 10:11 p.m.