Triple

T13419324
Position Surface form Disambiguated ID Type / Status
Subject Harry Callahan E313297 entity
Predicate givenName P17 FINISHED
Object Harry
Harry is the tough, no-nonsense San Francisco police inspector famously known as "Dirty Harry" from the American crime film series.
 E1038341 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: Harry | Statement: [Harry Callahan, givenName, Harry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harry
Context triple: [Harry Callahan, givenName, Harry]
  • A. Harry
    Harry is the given name of Harry Gregson-Williams, a prominent British film composer and music producer known for his work on numerous Hollywood soundtracks.
  • B. Harry
    Harry is the given name of American character actor and musician Harry Dean Stanton, known for his distinctive roles in film and television.
  • C. Harry
    Harry is the given name of Lord Woolf, a prominent British judge and former Lord Chief Justice of England and Wales.
  • D. Harry
    Harry is the given first name of Major League Baseball manager and former pitcher Bud Black.
  • E. Harry
    Harry is a character in the Peaky Blinders universe who becomes a victim of Arthur Shelby’s violent control and exploitation.
  • 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: Harry
Triple: [Harry Callahan, givenName, Harry]
Generated description
Harry is the tough, no-nonsense San Francisco police inspector famously known as "Dirty Harry" from the American crime film series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harry
Target entity description: Harry is the tough, no-nonsense San Francisco police inspector famously known as "Dirty Harry" from the American crime film series.
  • A. Harry
    Harry is the given first name of the American outlaw better known by his nickname, the Sundance Kid.
  • B. Harry
    Harry is the given name of American character actor and musician Harry Dean Stanton, known for his distinctive roles in film and television.
  • C. Harry
    Harry is a character in the Peaky Blinders universe who becomes a victim of Arthur Shelby’s violent control and exploitation.
  • D. Harry
    Harry is the given name of British Army officer Reginald Dyer, infamous for ordering the 1919 Jallianwala Bagh massacre in Amritsar, India.
  • E. Harry
    Harry is the nickname of Harry Karstens, the American outdoorsman and guide best known as the first superintendent of Denali National Park and a key figure in the first successful ascent of Denali.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb98e808190948013e8f24779c6 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73082a2548190aefc0f202b84165c completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f7311f14988190989e319741ef0ccf completed May 3, 2026, 11:27 a.m.
NED2 Entity disambiguation (via description) batch_69f731e24d508190a896875210be3189 completed May 3, 2026, 11:30 a.m.
Created at: April 9, 2026, 9:39 p.m.