Triple

T14577185
Position Surface form Disambiguated ID Type / Status
Subject Michael Frank E342082 entity
Predicate familyName P18 FINISHED
Object Frank
Frank is a common Germanic-origin surname borne by numerous individuals across various cultures and professions.
E203979 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: Frank | Statement: [Michael Frank, familyName, Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank
Context triple: [Michael Frank, familyName, Frank]
  • A. Frank
    Frank is the given name of Frank Lautenberg, a long-serving United States Senator from New Jersey known for his work on public health and transportation safety.
  • B. Frank
    Frank is the nickname of Frank Sheeran, an American labor union official and alleged mob hitman whose life inspired the film "The Irishman."
  • C. Frank
    Frank is the given name of Frank Herbert, the renowned American science fiction author best known for writing the novel "Dune."
  • D. Frank
    Frank is the given name of the American comic book writer, artist, and film director Frank Miller, known for works like "The Dark Knight Returns," "Sin City," and "300."
  • E. Frank
    Frank is the given name of Frank Brangwyn, a renowned British painter, muralist, and designer associated with the Arts and Crafts movement.
  • 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: Frank
Triple: [Michael Frank, familyName, Frank]
Generated description
Frank is a common Germanic-origin surname borne by numerous individuals across various cultures and professions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank
Target entity description: Frank is a common Germanic-origin surname borne by numerous individuals across various cultures and professions.
  • A. Frank chosen
    Frank is a common surname of Germanic origin borne by numerous notable individuals across politics, arts, and other fields.
  • B. Frank
    Frank is a masculine given name of Germanic origin meaning "free man," commonly used in English-speaking countries.
  • C. Frank
    Frank is the given name of Frank Lampard, the renowned English former professional footballer and manager.
  • D. Frank
    Frank is the given name of the renowned American architect Frank Lloyd Wright, a pivotal figure in modern architecture.
  • E. Frank
    Frank is the given name of Frank Oz, the renowned puppeteer, actor, and director best known for his work with the Muppets and on Star Wars.
  • F. None of above.

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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f5ec448190b2ef887fdf7b633e completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ace7da48190880a736ead5c4055 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8bb3c1188190b158d30e9c962911 completed May 8, 2026, 7:07 a.m.
NED2 Entity disambiguation (via description) batch_69fd8c6e7d448190835f87e27c998623 completed May 8, 2026, 7:10 a.m.
Created at: April 10, 2026, 1:24 a.m.