Triple

T5356134
Position Surface form Disambiguated ID Type / Status
Subject Don Siegel E102695 entity
Predicate directed P7373 FINISHED
Object Madigan
Madigan is a 1968 American crime drama film starring Richard Widmark as a tough New York City police detective navigating corruption and moral ambiguity.
 E514174 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: Madigan | Statement: [Don Siegel, directed, Madigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Madigan
Context triple: [Don Siegel, directed, Madigan]
  • A. Corrigan
    Corrigan is an Irish-origin surname borne by numerous notable figures in fields such as religion, politics, sports, and entertainment.
  • B. Govandi
    Govandi is a densely populated neighborhood in eastern Mumbai known for its informal settlements, industrial areas, and proximity to major transport routes.
  • C. Mulally
    Mulally is the surname of Alan Mulally, the American engineer and former CEO known for leading major turnarounds at Boeing and Ford Motor Company.
  • D. McDermid
    McDermid is a Scottish surname, often a variant of McDiarmid, borne by various individuals of Scottish and Irish heritage.
  • E. Millard
    Millard is the given name of Millard Fillmore, the 13th president of the United States.
  • 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: Madigan
Triple: [Don Siegel, directed, Madigan]
Generated description
Madigan is a 1968 American crime drama film starring Richard Widmark as a tough New York City police detective navigating corruption and moral ambiguity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Madigan
Target entity description: Madigan is a 1968 American crime drama film starring Richard Widmark as a tough New York City police detective navigating corruption and moral ambiguity.
  • A. Corrigan
    Corrigan is an Irish-origin surname borne by numerous notable figures in fields such as religion, politics, sports, and entertainment.
  • B. Govandi
    Govandi is a densely populated neighborhood in eastern Mumbai known for its informal settlements, industrial areas, and proximity to major transport routes.
  • C. Mulally
    Mulally is the surname of Alan Mulally, the American engineer and former CEO known for leading major turnarounds at Boeing and Ford Motor Company.
  • D. McDermid
    McDermid is a Scottish surname, often a variant of McDiarmid, borne by various individuals of Scottish and Irish heritage.
  • E. Millard
    Millard is the given name of Millard Fillmore, the 13th president of the United States.
  • 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_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd862f0ea48190bec78690ab3bee51 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21e2b7b08190aca4c2855ff041de completed March 21, 2026, 10:55 p.m.
NEDg Description generation batch_69bf228956d481909e9f3c11f4597cce completed March 21, 2026, 10:58 p.m.
NED2 Entity disambiguation (via description) batch_69bf230b571481909f76ada72d94c8d8 completed March 21, 2026, 11 p.m.
Created at: March 20, 2026, 2:01 p.m.