Triple

T7206729
Position Surface form Disambiguated ID Type / Status
Subject Roseanne E148683 entity
Predicate starring P1507 FINISHED
Object Michael Fishman
Michael Fishman is an American actor best known for playing D.J. Conner on the long-running sitcom "Roseanne" and its revival.
E689225 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 Fishman | Statement: [Roseanne, starring, Michael Fishman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Fishman
Context triple: [Roseanne, starring, Michael Fishman]
  • A. Eric Tannenbaum
    Eric Tannenbaum is a television producer best known for his work on popular American sitcoms, including serving as an executive producer on "Two and a Half Men."
  • B. Michael Berman
    Michael Berman is a writer and contributor known for his work published in George magazine.
  • C. Alan H. Fishman
    Alan H. Fishman is an American banking executive best known for briefly serving as CEO of Washington Mutual during its 2008 financial collapse.
  • D. Michael Bluestein
    Michael Bluestein is an American keyboardist and songwriter best known as a longtime member of the rock band Foreigner.
  • E. Michael Kagan
    Michael Kagan is an Israeli technologist and entrepreneur best known as the co-founder and longtime chief technology officer of high-performance networking company Mellanox Technologies.
  • 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 Fishman
Triple: [Roseanne, starring, Michael Fishman]
Generated description
Michael Fishman is an American actor best known for playing D.J. Conner on the long-running sitcom "Roseanne" and its revival.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Fishman
Target entity description: Michael Fishman is an American actor best known for playing D.J. Conner on the long-running sitcom "Roseanne" and its revival.
  • A. Eric Tannenbaum
    Eric Tannenbaum is a television producer best known for his work on popular American sitcoms, including serving as an executive producer on "Two and a Half Men."
  • B. Michael Berman
    Michael Berman is a writer and contributor known for his work published in George magazine.
  • C. Alan H. Fishman
    Alan H. Fishman is an American banking executive best known for briefly serving as CEO of Washington Mutual during its 2008 financial collapse.
  • D. Michael Bluestein
    Michael Bluestein is an American keyboardist and songwriter best known as a longtime member of the rock band Foreigner.
  • E. Michael Kagan
    Michael Kagan is an Israeli technologist and entrepreneur best known as the co-founder and longtime chief technology officer of high-performance networking company Mellanox Technologies.
  • 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_69c687e8cf188190b5f3ecffd681f04e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e969c5fc819096bc03bfba12d0cf completed March 27, 2026, 8:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8f2ffec108190ab60b0777d97dd89 completed March 29, 2026, 9:38 a.m.
NEDg Description generation batch_69c8f39c8cdc81908918d6dc5948012e completed March 29, 2026, 9:40 a.m.
NED2 Entity disambiguation (via description) batch_69c8f46ab5ec819092508ddedc816c89 completed March 29, 2026, 9:44 a.m.
Created at: March 27, 2026, 2:52 p.m.