Triple
T8312148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Venta Silurum |
E194614
|
entity |
| Predicate | modernSiteName |
P1213
|
FINISHED |
| Object | Caerwent |
E425197
|
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: Caerwent | Statement: [Venta Silurum, modernSiteName, Caerwent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caerwent Context triple: [Venta Silurum, modernSiteName, Caerwent]
-
A.
Caerwent
chosen
Caerwent is a historic village in Monmouthshire, Wales, best known for its remarkably well-preserved Roman town walls and archaeological remains.
-
B.
Caerleon
Caerleon is a historic town in South Wales traditionally associated with Arthurian legend as one of the possible locations of King Arthur’s court.
-
C.
Abergavenny
Abergavenny is a historic market town in Monmouthshire, Wales, known as a gateway to the Brecon Beacons and for its annual food festival.
-
D.
Caennais
Caennais refers to the inhabitants or natives of Caen, a historic city in the Normandy region of northwestern France.
-
E.
Trellech
Trellech is a historic village in Monmouthshire, Wales, known for its medieval significance and as the birthplace of philosopher Bertrand Russell.
- 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_69ca82e6e2648190a31eaf6f4f757b2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f504ca8819087fb1f731f7a7cfd |
completed | March 31, 2026, 8:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce0278b9a88190a57a6b1b31c39ee8 |
completed | April 2, 2026, 5:45 a.m. |
Created at: March 30, 2026, 5:54 p.m.