Triple

T2924349
Position Surface form Disambiguated ID Type / Status
Subject Salamanca Market E78806 entity
Predicate near P350 FINISHED
Object Battery Point E78804 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: Battery Point | Statement: [Salamanca Market, near, Battery Point]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Battery Point
Context triple: [Salamanca Market, near, Battery Point]
  • A. Battery Point chosen
    Battery Point is a historic waterfront suburb of Hobart, Tasmania, known for its well-preserved colonial architecture and village-like streets.
  • B. Battery Pier
    Battery Pier is a harbour pier located in Douglas, Isle of Man, serving as part of the town’s maritime infrastructure.
  • C. The Battery
    The Battery is a historic waterfront park at the southern tip of Manhattan in New York City, known for its harbor views, ferries to the Statue of Liberty and Ellis Island, and landmark Castle Clinton.
  • D. The Battery
    The Battery is a historic defensive seawall and promenade in Charleston, South Carolina, famed for its antebellum homes and views of Charleston Harbor and Fort Sumter.
  • E. Charger
    Charger is the NATO reporting name for the Soviet-era Tupolev Tu-144, one of the world’s first supersonic passenger airliners.
  • 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_69ad8b0d40b481908bc2a5fa2e73c3fb completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad97bf2df88190bd4f1e90d4656507 completed March 8, 2026, 3:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69b056375b5c819081c7d4fd506cbf25 completed March 10, 2026, 5:34 p.m.
Created at: March 8, 2026, 2:55 p.m.