Triple

T20742612
Position Surface form Disambiguated ID Type / Status
Subject High Windows E510480 entity
Predicate hasPoem P21160 FINISHED
Object The Building 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: The Building | Statement: [High Windows, hasPoem, The Building]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Building
Context triple: [High Windows, hasPoem, The Building]
  • A. The Building chosen
    The Building is a short-lived 1993 American sitcom created by and starring Bonnie Hunt, known for its improvisational style and ensemble cast of Chicago Second City alumni.
  • B. Building A
    Building A is one of the main exhibition and convention halls within the Georgia World Congress Center complex in Atlanta, Georgia.
  • C. Building A
    Building A is a major warehouse and industrial structure within the historic Brooklyn Army Terminal complex in Brooklyn, New York.
  • D. Main Building
    Main Building is the iconic, historic central structure on Vassar College’s campus, known for its distinctive architecture and role as a focal point of college life.
  • E. Main Building
    The Main Building is the central conference and event facility within the World Conference Center Bonn complex in Bonn, Germany.
  • 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_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c210a2c08190bd767df3188bb401 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:33 p.m.