Triple

T13083656
Position Surface form Disambiguated ID Type / Status
Subject Larry Gelbart E310273 entity
Predicate familyName P18 FINISHED
Object Gelbart
Gelbart is a surname most notably associated with Larry Gelbart, the American comedy writer and co-creator of the M*A*S*H television series.
 E1019716 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: Gelbart | Statement: [Larry Gelbart, familyName, Gelbart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gelbart
Context triple: [Larry Gelbart, familyName, Gelbart]
  • A. Weinberger
    Weinberger is a music publishing company known for issuing classical works, including compositions by major Romantic-era composers.
  • B. Weinberger
    Weinberger is a German-origin surname most notably associated with Caspar Weinberger, a former U.S. Secretary of Defense.
  • C. Lipsett
    Lipsett is a surname of English and Irish origin borne by various notable individuals across fields such as the military, politics, and the arts.
  • D. Liebermann
    Liebermann is a German surname most notably associated with figures such as Max Liebermann, a prominent Impressionist painter and leading member of the Berlin Secession.
  • E. Wilentz
    Wilentz is a notable American family name associated with several prominent figures in law, politics, and academia.
  • 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: Gelbart
Triple: [Larry Gelbart, familyName, Gelbart]
Generated description
Gelbart is a surname most notably associated with Larry Gelbart, the American comedy writer and co-creator of the M*A*S*H television series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gelbart
Target entity description: Gelbart is a surname most notably associated with Larry Gelbart, the American comedy writer and co-creator of the M*A*S*H television series.
  • A. Weinberger
    Weinberger is a music publishing company known for issuing classical works, including compositions by major Romantic-era composers.
  • B. Weinberger
    Weinberger is a German-origin surname most notably associated with Caspar Weinberger, a former U.S. Secretary of Defense.
  • C. Lipsett
    Lipsett is a surname of English and Irish origin borne by various notable individuals across fields such as the military, politics, and the arts.
  • D. Liebermann
    Liebermann is a German surname most notably associated with figures such as Max Liebermann, a prominent Impressionist painter and leading member of the Berlin Secession.
  • E. Wilentz
    Wilentz is a notable American family name associated with several prominent figures in law, politics, and academia.
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d9811add9881908a92186dab5b6d48 completed April 10, 2026, 11 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d60e7b48819087e4583a5736c1df completed May 3, 2026, 4:58 a.m.
NEDg Description generation batch_69f6d76cc33c8190ac8113094bcf868b completed May 3, 2026, 5:04 a.m.
NED2 Entity disambiguation (via description) batch_69f6d8013e9481908f5edcce7247212d completed May 3, 2026, 5:07 a.m.
Created at: April 9, 2026, 9:02 p.m.