Triple

T20672042
Position Surface form Disambiguated ID Type / Status
Subject FNB Field E508051 entity
Predicate location P40 FINISHED
Object City Island E1178526 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: City Island | Statement: [FNB Field, location, City Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City Island
Context triple: [FNB Field, location, City Island]
  • A. City Island
    City Island is a small, historic seaside neighborhood in New York City known for its maritime heritage, seafood restaurants, and village-like atmosphere.
  • B. City Island chosen
    City Island is a small recreational island in the Susquehanna River in Harrisburg, Pennsylvania, known for its sports facilities, parks, and family attractions.
  • C. The Toast of New York
    The Toast of New York is a 1937 American historical drama film set in the post–Civil War era, known for its portrayal of financier Jim Fisk and featuring Frances Farmer in a prominent role.
  • D. The Atlantic City Story
    The Atlantic City Story is an independent drama film featuring Mike Faist in a prominent role.
  • E. Vanity Row
    "Vanity Row" is a hardboiled crime novel by W. R. Burnett, known for its gritty portrayal of political corruption and underworld intrigue in an American city.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5cb1fc88190805f623e93a70368 completed April 20, 2026, 11:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08cd66b6b88190a863948cb31c9af7 completed May 16, 2026, 8:02 p.m.
Created at: April 16, 2026, 11:44 a.m.