Triple

T10836719
Position Surface form Disambiguated ID Type / Status
Subject Central Intelligence E255777 entity
Predicate editedBy P1954 FINISHED
Object Michael L. Sale
Michael L. Sale is an editor known for his work on the publication "Central Intelligence."
E891644 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: Michael L. Sale | Statement: [Central Intelligence, editedBy, Michael L. Sale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael L. Sale
Context triple: [Central Intelligence, editedBy, Michael L. Sale]
  • A. Michael L. Sale
    Michael L. Sale is a film editor known for his work on major Hollywood comedies, including the hit movie "Bridesmaids."
  • B. Michael J. Weithorn
    Michael J. Weithorn is an American television writer and producer best known for creating and working on several sitcoms, including "Ned and Stacey" and "The King of Queens."
  • C. Michael W. Burns
    Michael W. Burns is an actor known for his role in the Western television miniseries "Broken Trail."
  • D. Eric A. Sears
    Eric A. Sears is a film editor known for his work on the 2015 horror-comedy movie "Krampus."
  • E. Stephen F. Martin
    Stephen F. Martin is an American organic chemist renowned for his influential research in synthetic methodology and complex molecule synthesis.
  • 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: Michael L. Sale
Triple: [Central Intelligence, editedBy, Michael L. Sale]
Generated description
Michael L. Sale is an editor known for his work on the publication "Central Intelligence."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael L. Sale
Target entity description: Michael L. Sale is an editor known for his work on the publication "Central Intelligence."
  • A. Michael L. Sale
    Michael L. Sale is a film editor known for his work on major Hollywood comedies, including the hit movie "Bridesmaids."
  • B. Michael J. Weithorn
    Michael J. Weithorn is an American television writer and producer best known for creating and working on several sitcoms, including "Ned and Stacey" and "The King of Queens."
  • C. Michael W. Burns
    Michael W. Burns is an actor known for his role in the Western television miniseries "Broken Trail."
  • D. Eric A. Sears
    Eric A. Sears is a film editor known for his work on the 2015 horror-comedy movie "Krampus."
  • E. Stephen F. Martin
    Stephen F. Martin is an American organic chemist renowned for his influential research in synthetic methodology and complex molecule synthesis.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d746ff70148190b844ab92d796af6c completed April 9, 2026, 6:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e154a582188190af96ae0d5cc08dc4 completed April 16, 2026, 9:29 p.m.
NEDg Description generation batch_69e1739ed9b88190949125759f42efd2 completed April 16, 2026, 11:41 p.m.
NED2 Entity disambiguation (via description) batch_69e175ecef0c8190b08052d751f1a608 completed April 16, 2026, 11:51 p.m.
Created at: April 8, 2026, 9:19 p.m.