Triple
T17010540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Britannia |
E412686
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Londinium |
E194612
|
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: Londinium | Statement: [Britannia, capital, Londinium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Londinium Context triple: [Britannia, capital, Londinium]
-
A.
Londinium
chosen
Londinium was the major Roman city and commercial hub that later evolved into modern-day London.
-
B.
Camulodunum
Camulodunum was an important ancient Roman town in Britain, serving as the first provincial capital and a major military and administrative center.
-
C.
Dacorum
Dacorum is a local government district and borough in Hertfordshire, England, encompassing towns such as Hemel Hempstead and Berkhamsted.
-
D.
Verulamium
Verulamium was a major Roman town in Britain, located near modern St Albans, known for its archaeological remains including mosaics, a theatre, and city walls.
-
E.
Eboracum
Eboracum was the major Roman fortress and city that later became the English city of York, serving as an important military and administrative center in Roman Britain.
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d47bcb508190a799f0bad6b70245 |
completed | April 18, 2026, 6:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc241ec88190a3e868ab88b26f09 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:33 a.m.