Triple

T16079624
Position Surface form Disambiguated ID Type / Status
Subject Donald Crone E390070 entity
Predicate notableWork P4 FINISHED
Object Sydney Tower E59441 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: Sydney Tower | Statement: [Donald Crone, notableWork, Sydney Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sydney Tower
Context triple: [Donald Crone, notableWork, Sydney Tower]
  • A. Sydney Tower chosen
    Sydney Tower is a prominent observation and communications tower in Sydney, Australia, known for its panoramic city views and status as one of the city's most recognizable landmarks.
  • B. Telstra Tower
    Telstra Tower is a prominent telecommunications and observation tower in Canberra, Australia, offering panoramic views of the city and surrounding region.
  • C. Canton Tower
    Canton Tower is a landmark supertall observation and telecommunications tower in Guangzhou, China, known for its distinctive twisting design and panoramic city views.
  • D. Eureka Opera House
    The Eureka Opera House is a restored 19th-century performance hall and cultural landmark in the historic mining town of Eureka, Nevada.
  • E. UTS Tower
    UTS Tower is the main high-rise campus building of the University of Technology Sydney and one of the most recognizable landmarks in Sydney’s educational precinct.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18448bebc8190b0e84b1da097bf8b completed April 17, 2026, 12:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe48adec081909623355eabee472c completed May 10, 2026, 1:51 a.m.
Created at: April 10, 2026, 4:57 a.m.