Triple

T13564445
Position Surface form Disambiguated ID Type / Status
Subject Dann Florek E323995 entity
Predicate notableCharacter P1481 FINISHED
Object Donald Cragen E820596 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: Donald Cragen | Statement: [Dann Florek, notableCharacter, Donald Cragen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Cragen
Context triple: [Dann Florek, notableCharacter, Donald Cragen]
  • A. Donald Cragen chosen
    Donald Cragen is a fictional NYPD captain known for leading the Special Victims Unit with a firm but compassionate approach in the television series "Law & Order: Special Victims Unit."
  • B. Andy Sipowicz
    Andy Sipowicz is a tough, emotionally complex New York City detective and central character from the television drama "NYPD Blue."
  • C. Mickey Hargitay
    Mickey Hargitay was a Hungarian-American bodybuilder, actor, and former Mr. Universe best known for his marriage to Jayne Mansfield and his roles in 1950s–60s films.
  • D. Val McNulty
    Val McNulty is a fictional character appearing in P. G. Wodehouse’s comic novel "The Mating Season."
  • E. Paul Sciarra
    Paul Sciarra is an American entrepreneur best known as a co-founder of the visual discovery and bookmarking platform Pinterest.
  • 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_69d8076830b48190910a902bae5888e2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb00bbe848190bb33efe2af528295 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bb1ef508190ab587bd2aa34795b completed May 3, 2026, 3:37 p.m.
Created at: April 9, 2026, 9:47 p.m.