Triple

T17904918
Position Surface form Disambiguated ID Type / Status
Subject Michael Pitt E447675 entity
Predicate playedCharacter P1507 FINISHED
Object Henry
Henry is a fictional character portrayed by American actor Michael Pitt, known for his intense and often complex roles in film and television.
E1294769 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: Henry | Statement: [Michael Pitt, playedCharacter, Henry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry
Context triple: [Michael Pitt, playedCharacter, Henry]
  • A. Henry
    Henry is the given name of the influential American architect Henry Hobson Richardson, a key figure in 19th-century architecture.
  • B. Henry
    Henry is a character who serves as the narrator in the 1933 film "The Power and the Glory," providing the story’s perspective and framing its events.
  • C. Henry
    Henry was a medieval Polish duke known as Henry the Bearded, a powerful Piast ruler who significantly influenced the politics of Silesia and Greater Poland.
  • D. Henry
    Henry is the given first name of Harry Wright, the 19th-century English-born American baseball player and manager often called the "Father of Professional Baseball."
  • E. Henry
    Henry is the given name of Admiral Sir Henry Leach, a prominent British Royal Navy officer and former First Sea Lord.
  • 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: Henry
Triple: [Michael Pitt, playedCharacter, Henry]
Generated description
Henry is a fictional character portrayed by American actor Michael Pitt, known for his intense and often complex roles in film and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Henry
Target entity description: Henry is a fictional character portrayed by American actor Michael Pitt, known for his intense and often complex roles in film and television.
  • A. Henry
    Henry is the disturbed serial killer protagonist of the cult horror film "Henry: Portrait of a Serial Killer," portrayed by Michael Rooker.
  • B. Henry
    Henry is a character from the film "The Farewell," portrayed as the young grandson navigating family expectations and cultural differences during his grandmother’s terminal illness.
  • C. Henry
    Henry is a character who serves as the narrator in the 1933 film "The Power and the Glory," providing the story’s perspective and framing its events.
  • D. Henry
    Henry is the given name of American silent film actor Henry B. Walthall, known for his roles in early 20th-century cinema.
  • E. Henry
    Henry is a character in Simon Gray's stage play "Quartermaine's Terms," which portrays the personal and professional lives of teachers at a 1960s Cambridge language school.
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9b643c8190a01e9ec4caa88183 completed April 19, 2026, 9:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a031b1f2fec81909b3cf0392275a2ff completed May 12, 2026, 12:20 p.m.
NEDg Description generation batch_6a031c245ee08190851b20d547a7946c completed May 12, 2026, 12:25 p.m.
NED2 Entity disambiguation (via description) batch_6a031c89d46881908cf88e5396e1d08e completed May 12, 2026, 12:26 p.m.
Created at: April 10, 2026, 10:19 a.m.