Triple

T18275314
Position Surface form Disambiguated ID Type / Status
Subject The Fleet lagoon E437718 entity
Predicate near P350 FINISHED
Object Portland NE NERFINISHED

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: Portland | Statement: [The Fleet lagoon, near, Portland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Portland
Context triple: [The Fleet lagoon, near, Portland]
  • A. Portland
    Portland is a small historic town in the Central Tablelands region of New South Wales, Australia, known for its early cement works and heritage streetscapes.
  • B. Portland
    Portland is the largest city in Oregon, known for its vibrant arts scene, progressive culture, and lush green spaces in the Pacific Northwest.
  • C. Portland
    Portland is the largest city in the U.S. state of Maine, known for its historic waterfront, vibrant arts scene, and coastal New England charm.
  • D. Portland chosen
    Portland is a tied island and civil parish on the Jurassic Coast in Dorset, England, known for its historic quarries, lighthouse, and role as a former naval base.
  • E. Portlands
    Portlands is a residential suburb within Mitchells Plain, a large township on the Cape Flats in Cape Town, South Africa.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50051bccc8190832eacdb6945d6b7 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:34 a.m.