Triple

T17898267
Position Surface form Disambiguated ID Type / Status
Subject P. J. Brown E447490 entity
Predicate nickname P55 FINISHED
Object P. J. Brown 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: P. J. Brown | Statement: [P. J. Brown, nickname, P. J. Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: P. J. Brown
Context triple: [P. J. Brown, nickname, P. J. Brown]
  • A. P. J. Brown chosen
    P. J. Brown is a former American professional basketball player best known for his long NBA career as a defensive-minded power forward and center.
  • B. Patricia Terrill
    Patricia Terrill is a central female character in the 1958 Western film "The Big Country," known for her romantic involvement with James McKay and her role in the story’s frontier family conflict.
  • C. Catherine Block
    Catherine Block is a historic building within the Peterhof Palace complex near St. Petersburg, Russia, originally designed as a residence associated with Empress Catherine I.
  • D. Ann C. Crispin
    Ann C. Crispin was an American science fiction and tie-in novelist best known for her Star Trek and Star Wars books and for co-founding the writers’ advocacy group Writer Beware.
  • E. Linda Howard
    Linda Howard is a fictional protagonist featured in the film "Lost in America."
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d8122b481909992356f3f575858 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.