Triple

T15717256
Position Surface form Disambiguated ID Type / Status
Subject 550 Madison Avenue E380992 entity
Predicate formerTenant P7727 FINISHED
Object AT&T E89783 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: AT&T | Statement: [550 Madison Avenue, formerTenant, AT&T]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AT&T
Context triple: [550 Madison Avenue, formerTenant, AT&T]
  • A. AT&T chosen
    AT&T is a major American telecommunications conglomerate known for providing wireless, internet, and media services nationwide.
  • B. Verizon
    Verizon is a major American telecommunications company providing wireless, internet, and related communication services across the United States and globally.
  • C. Bell Atlantic
    Bell Atlantic was a major U.S. telecommunications company formed after the breakup of AT&T, which later merged with GTE to become Verizon Communications.
  • D. Ameritech
    Ameritech was a regional telecommunications company formed after the breakup of AT&T’s Bell System, serving the Midwestern United States with local and long-distance phone services.
  • E. Alltel
    Alltel was a major American wireless telecommunications company that provided mobile phone services across numerous U.S. states before being largely acquired by Verizon Wireless.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f91beb08190bd91bf9306737c3b completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82f464008190ae0e79f50b9b3eb3 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:45 a.m.