Triple

T4064401
Position Surface form Disambiguated ID Type / Status
Subject Bankside Power Station E86289 entity
Predicate nearbyLandmark P350 FINISHED
Object Shakespeare’s Globe E112976 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: Shakespeare’s Globe | Statement: [Bankside Power Station, nearbyLandmark, Shakespeare’s Globe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shakespeare’s Globe
Context triple: [Bankside Power Station, nearbyLandmark, Shakespeare’s Globe]
  • A. The Globe Theatre chosen
    The Globe Theatre was a famous Elizabethan playhouse in London closely associated with William Shakespeare and the performance of many of his plays.
  • B. Globe Theatre
    The Globe Theatre was the former name of the Lunt-Fontanne Theatre, a prominent Broadway theater in New York City.
  • C. The Globe
    The Globe is a traditional English pub serving as a local social hub in the village of Luddenden Foot in West Yorkshire.
  • D. The Globe
    The Globe is a distinctive spherical fine-dining restaurant in Riyadh, Saudi Arabia, known for its panoramic city views from atop the Al Faisaliyah Center.
  • E. The Globe
    The Globe is a major American daily newspaper based in Boston, widely recognized for its influential journalism and multiple Pulitzer Prize–winning investigations.
  • 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbf44c888190b5746d93e9f8e3a3 completed March 9, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562ae949c819092affaaca97c16d1 completed March 14, 2026, 1:29 p.m.
Created at: March 9, 2026, 3:38 p.m.