Triple

T15728766
Position Surface form Disambiguated ID Type / Status
Subject Betty Field E381285 entity
Predicate spouse P13 FINISHED
Object Edwin Sherin
Edwin Sherin was an American theater and television director and producer, best known for his work on the long-running TV series "Law & Order."
E1272792 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: Edwin Sherin | Statement: [Betty Field, spouse, Edwin Sherin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edwin Sherin
Context triple: [Betty Field, spouse, Edwin Sherin]
  • A. Stephen Wainger
    Stephen Wainger is an American mathematician known for his contributions to harmonic analysis and related areas of analysis.
  • B. Andrew Shulkind
    Andrew Shulkind is a cinematographer known for his atmospheric and visually immersive work in genre films and television.
  • C. Jay O. Rothman
    Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
  • D. Joseph Wechsler
    Joseph Wechsler was an individual of sufficient local or historical significance to be recognized as a notable burial at Mount Olivet Cemetery in Frederick, Maryland.
  • E. Edwin Schlossberg
    Edwin Schlossberg is an American designer, artist, and author known for his innovative work in interactive museum and exhibition design.
  • 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: Edwin Sherin
Triple: [Betty Field, spouse, Edwin Sherin]
Generated description
Edwin Sherin was an American theater and television director and producer, best known for his work on the long-running TV series "Law & Order."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Edwin Sherin
Target entity description: Edwin Sherin was an American theater and television director and producer, best known for his work on the long-running TV series "Law & Order."
  • A. Stephen Wainger
    Stephen Wainger is an American mathematician known for his contributions to harmonic analysis and related areas of analysis.
  • B. Andrew Shulkind
    Andrew Shulkind is a cinematographer known for his atmospheric and visually immersive work in genre films and television.
  • C. Jay O. Rothman
    Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
  • D. Joseph Wechsler
    Joseph Wechsler was an individual of sufficient local or historical significance to be recognized as a notable burial at Mount Olivet Cemetery in Frederick, Maryland.
  • E. Edwin Schlossberg
    Edwin Schlossberg is an American designer, artist, and author known for his innovative work in interactive museum and exhibition design.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb4cc0081909efe330339474017 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c1e360048190a94b9ce8724cb4b7 completed May 11, 2026, 11:47 a.m.
NEDg Description generation batch_6a01c60989d08190839909d7018f48f4 completed May 11, 2026, 12:05 p.m.
NED2 Entity disambiguation (via description) batch_6a01c701504c8190ad1979b65cb73336 completed May 11, 2026, 12:09 p.m.
Created at: April 10, 2026, 4:46 a.m.