Triple

T15600813
Position Surface form Disambiguated ID Type / Status
Subject Doctor Detroit E375026 entity
Predicate screenwriter P2831 FINISHED
Object Barry Blumberg
Barry Blumberg is a screenwriter best known for his work on the 1983 comedy film "Doctor Detroit."
E1167369 NE FINISHED

How this triple was built (4 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: Barry Blumberg | Statement: [Doctor Detroit, screenwriter, Barry Blumberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barry Blumberg
Context triple: [Doctor Detroit, screenwriter, Barry Blumberg]
  • A. Harvey Shine
    Harvey Shine is the middle-aged, down-on-his-luck jingle writer portrayed by Dustin Hoffman in the romantic drama film "Last Chance Harvey."
  • B. Steven G. Ehrlich
    Steven G. Ehrlich is an American jurist who served as a justice on the Florida Supreme Court.
  • C. Robert Weinberg
    Robert Weinberg is a prominent American cancer biologist best known for his pioneering work on oncogenes and tumor suppressor genes, which helped establish the molecular basis of cancer.
  • D. David H. Kurtzman
    David H. Kurtzman was a Pennsylvania state education official best known as the named defendant in the landmark U.S. Supreme Court case Lemon v. Kurtzman, which established the modern test for violations of the Establishment Clause.
  • E. Michael Berman
    Michael Berman is a writer and contributor known for his work published in George magazine.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Barry Blumberg
Triple: [Doctor Detroit, screenwriter, Barry Blumberg]
Generated description
Barry Blumberg is a screenwriter best known for his work on the 1983 comedy film "Doctor Detroit."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Barry Blumberg
Target entity description: Barry Blumberg is a screenwriter best known for his work on the 1983 comedy film "Doctor Detroit."
  • A. Harvey Shine
    Harvey Shine is the middle-aged, down-on-his-luck jingle writer portrayed by Dustin Hoffman in the romantic drama film "Last Chance Harvey."
  • B. Steven G. Ehrlich
    Steven G. Ehrlich is an American jurist who served as a justice on the Florida Supreme Court.
  • C. Robert Weinberg
    Robert Weinberg is a prominent American cancer biologist best known for his pioneering work on oncogenes and tumor suppressor genes, which helped establish the molecular basis of cancer.
  • D. David H. Kurtzman
    David H. Kurtzman was a Pennsylvania state education official best known as the named defendant in the landmark U.S. Supreme Court case Lemon v. Kurtzman, which established the modern test for violations of the Establishment Clause.
  • E. Michael Berman
    Michael Berman is a writer and contributor known for his work published in George magazine.
  • F. None of above. chosen

Provenance (5 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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e621fc4819097e8e85e7ddfdc6c completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56cf8e5c8190bf13114ab0a834de completed May 9, 2026, 3:46 p.m.
NEDg Description generation batch_69ff5acd35648190a204b78f7fb9619c completed May 9, 2026, 4:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff5b3f71148190a96c6f396512c1fd completed May 9, 2026, 4:05 p.m.
Created at: April 10, 2026, 4:12 a.m.