Triple

T3366117
Position Surface form Disambiguated ID Type / Status
Subject Louis Sullivan E70838 entity
Predicate notableWork P4 FINISHED
Object Auditorium Building E73977 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: Auditorium Building | Statement: [Louis Sullivan, notableWork, Auditorium Building]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Auditorium Building
Context triple: [Louis Sullivan, notableWork, Auditorium Building]
  • A. Auditorium Building chosen
    The Auditorium Building is a historic Chicago landmark renowned for its pioneering mixed-use design and exceptional acoustics, housing a theater, hotel, and offices in a single monumental structure.
  • B. Remis Auditorium
    Remis Auditorium is a performance and lecture venue located within the Museum of Fine Arts in Boston, used for films, talks, and cultural events.
  • C. Keller Auditorium
    Keller Auditorium is a major performing arts venue in downtown Portland, Oregon, hosting Broadway tours, concerts, and other large-scale cultural events.
  • D. Miller Auditorium
    Miller Auditorium is a major performing arts venue in Kalamazoo, Michigan, hosting concerts, Broadway tours, and other large-scale cultural events.
  • E. Auditorium Library
    Auditorium Library is an academic library of Roosevelt University, serving as a key research and study resource for its students and faculty.
  • 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_69ad85a729d48190afd789cd8417f289 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb287a30c8190b4c40091675c94fb completed March 8, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b325500eac8190b6f43864af8bda6c completed March 12, 2026, 8:42 p.m.
Created at: March 8, 2026, 3:13 p.m.