Triple

T2123917
Position Surface form Disambiguated ID Type / Status
Subject Cherbourg E43987 entity
Predicate connectsByFerryTo P1831 FINISHED
Object Portsmouth E18376 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: Portsmouth | Statement: [Cherbourg, connectsByFerryTo, Portsmouth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Portsmouth
Context triple: [Cherbourg, connectsByFerryTo, Portsmouth]
  • A. Portsmouth chosen
    Portsmouth is a historic naval port city on England’s south coast, heavily targeted and damaged during the World War II Blitz.
  • B. Portsmouth
    Portsmouth is a historic seaport city in southeastern New Hampshire known for its colonial-era architecture, maritime heritage, and vibrant cultural scene.
  • C. 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.
  • D. Portsmouth
    Portsmouth is a residential neighborhood in North Portland, Oregon, known for its parks, schools, and diverse community.
  • E. Norfolk
    Norfolk is a county in the East of England known for its rural landscapes, historic market towns, and extensive coastline along the North Sea.
  • 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_69a88717cfe48190b7ecdd68c824848a completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb55cb2c8190aab8199da3335032 completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f72ad8c81909da734f6316f747f completed March 9, 2026, 7:28 p.m.
Created at: March 4, 2026, 7:44 p.m.