Triple

T20390671
Position Surface form Disambiguated ID Type / Status
Subject Moon Bloodgood E498074 entity
Predicate spouse P13 FINISHED
Object Grady Hall NE NERFINISHED

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: Grady Hall | Statement: [Moon Bloodgood, spouse, Grady Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grady Hall
Context triple: [Moon Bloodgood, spouse, Grady Hall]
  • A. Grady Hall chosen
    Grady Hall is an American director and visual storyteller known for his work on high-profile music videos, commercials, and genre television projects.
  • B. Stetson Hall
    Stetson Hall is a historic civic building and prominent architectural landmark located in Randolph, Massachusetts.
  • C. Johnson Hall
    Johnson Hall is a historic 18th-century estate in Johnstown, New York, best known as the former home of Sir William Johnson, a prominent colonial leader and British Superintendent of Indian Affairs.
  • D. Correll Hall
    Correll Hall is an academic building at the University of Georgia that serves as a key facility for the Terry College of Business.
  • E. Bascom Hall
    Bascom Hall is the iconic main administrative building of the University of Wisconsin–Madison, prominently situated atop Bascom Hill and symbolizing the university’s historic campus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790f8d9c819093038f6bb6f47a92 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.