Triple

T10088911
Position Surface form Disambiguated ID Type / Status
Subject Satan Met a Lady E215290 entity
Predicate stars P1956 FINISHED
Object Porter Hall E456967 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: Porter Hall | Statement: [Satan Met a Lady, stars, Porter Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porter Hall
Context triple: [Satan Met a Lady, stars, Porter Hall]
  • A. Porter Hall chosen
    Porter Hall was an American character actor known for his memorable supporting roles in classic Hollywood films of the 1930s and 1940s.
  • B. Parmenter Hall
    Parmenter Hall is a historic academic building on the campus of Baker University in Baldwin City, Kansas.
  • C. Hubbard Hall
    Hubbard Hall is a historic building at Harvard University, located within the central campus area known as the Yard.
  • D. Kroon Hall
    Kroon Hall is a sustainably designed, LEED-certified building that serves as the main home of Yale University’s School of the Environment.
  • E. Winthrop Hall
    Winthrop Hall is a prominent heritage-listed ceremonial and event building on the University of Western Australia’s Crawley campus, known for its grand architecture and iconic clock tower.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd057e32881908bf630559af94906 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b693afac819090635d2eb147bdcb completed April 5, 2026, 7:22 p.m.
Created at: March 30, 2026, 9:01 p.m.