Triple

T1703689
Position Surface form Disambiguated ID Type / Status
Subject Watling Street E36821 entity
Predicate connects P390 FINISHED
Object Dover E31236 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: Dover | Statement: [Watling Street, connects, Dover]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dover
Context triple: [Watling Street, connects, Dover]
  • A. Dover
    Dover is a small town in eastern Dutchess County, New York, known for its rural character and location near the Connecticut border.
  • B. Dover
    Dover is one of the oldest permanent European settlements in what is now the U.S. state of New Hampshire, historically significant as an early colonial town and port.
  • C. Dover
    Dover is the capital city of the U.S. state of Delaware, known for its historic district, government institutions, and proximity to Delaware Bay.
  • D. Dover chosen
    Dover is a coastal town in southeast England best known for its white chalk cliffs and its strategic port facing the narrowest part of the English Channel.
  • E. Portsmouth
    Portsmouth is one of the earliest English settlements in what is now the state of Rhode Island, located on Aquidneck Island in Narragansett Bay.
  • 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_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62f25bac8190977d6f3bd79363cb completed March 6, 2026, 5:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7ed8b7a08190a39f4b90fbf68cd9 completed March 9, 2026, 8:03 a.m.
Created at: March 4, 2026, 7:30 p.m.