Triple

T424651
Position Surface form Disambiguated ID Type / Status
Subject Pier 39 E8179 entity
Predicate hasViewOf P854 FINISHED
Object Angel Island E6875 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: Angel Island | Statement: [Pier 39, hasViewOf, Angel Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angel Island
Context triple: [Pier 39, hasViewOf, Angel Island]
  • A. Angel Island chosen
    Angel Island is a historic island in San Francisco Bay known for its former U.S. immigration station, often called the "Ellis Island of the West."
  • B. Ellis Island
    Ellis Island is a historic immigration station in New York Harbor that served as the primary entry point for millions of immigrants to the United States from 1892 to 1954.
  • C. Asylum Hill
    Asylum Hill is a historic neighborhood in Hartford, Connecticut, known for its Victorian architecture, major insurance company headquarters, and cultural institutions.
  • D. La Espero
    La Espero is the poem by L. L. Zamenhof that serves as the de facto anthem of the international language Esperanto, expressing its ideals of peace and global understanding.
  • E. Harborland
    Harborland is a popular waterfront shopping and entertainment district in Kobe, Japan, known for its modern malls, restaurants, and scenic harbor views.
  • 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_69a2e7f1d1bc81909cf2dc9754a3c334 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2eed3e4cc8190ba6aff3bd1adb06f completed Feb. 28, 2026, 1:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a42a17403081909bcbbc0fdfdc25dc completed March 1, 2026, 11:59 a.m.
Created at: Feb. 28, 2026, 1:11 p.m.