Triple

T16578974
Position Surface form Disambiguated ID Type / Status
Subject Ermine Street E402788 entity
Predicate connects P390 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: [Ermine Street, connects, Londinium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Londinium
Context triple: [Ermine Street, connects, 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3595f9be88190b01ba628ecf1103d completed April 18, 2026, 10:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006eee7e4881908a529717bc449078 completed May 10, 2026, 11:41 a.m.
Created at: April 10, 2026, 5:16 a.m.