Triple

T8879872
Position Surface form Disambiguated ID Type / Status
Subject Key West Harbor E211381 entity
Predicate adjacentTo P224 FINISHED
Object Mallory Square E39979 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: Mallory Square | Statement: [Key West Harbor, adjacentTo, Mallory Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mallory Square
Context triple: [Key West Harbor, adjacentTo, Mallory Square]
  • A. Mallory Square chosen
    Mallory Square is a famous waterfront plaza in Key West, Florida, renowned for its nightly sunset celebrations featuring street performers, vendors, and views over the Gulf of Mexico.
  • B. Havelock Square
    Havelock Square is an area in Singapore known for housing key legal institutions, including the Family Justice Courts.
  • C. Lechmere Square
    Lechmere Square is a major commercial and transit hub in Cambridge, Massachusetts, known for its shopping center and as a key stop on the MBTA Green Line.
  • D. Portman Square
    Portman Square is a historic Georgian garden square in Marylebone, central London, known for its elegant townhouses and private members’ clubs.
  • E. Windsor Square
    Windsor Square is a historic, affluent residential neighborhood in central Los Angeles known for its large, early-20th-century homes and tree-lined streets.
  • 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_69ca838f9e20819096ab1f236a70381a completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61677c9c8190aa09dc2a05d4cf95 completed April 1, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc92c2f088190b953de2bfcbb5bb5 completed April 3, 2026, 2:05 p.m.
Created at: March 30, 2026, 6:52 p.m.