Triple

T4418109
Position Surface form Disambiguated ID Type / Status
Subject Frank Lampard E95026 entity
Predicate givenName P17 FINISHED
Object Frank
Frank is the given name of Frank Lampard, the renowned English former professional footballer and manager.
E437063 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: [Frank Lampard, givenName, Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank
Context triple: [Frank Lampard, givenName, Frank]
  • A. Frank
    Frank is a key supporting character in the post-apocalyptic horror film "28 Days Later," known as a protective father trying to keep his daughter safe amid a devastating viral outbreak in London.
  • B. Frank
    Frank is the Allied reporting name for the Japanese Nakajima Ki-84, a highly capable World War II fighter aircraft used by the Imperial Japanese Army Air Service.
  • C. Frank
    Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
  • D. Frank
    Frank is the given first name of the American contemporary street artist and graphic designer Shepard Fairey, known for his iconic "OBEY" and Barack Obama "Hope" posters.
  • E. Frank
    Frank is the given name of British screenwriter and children's author Frank Cottrell-Boyce.
  • 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: [Frank Lampard, givenName, Frank]
Generated description
Frank is the given name of Frank Lampard, the renowned English former professional footballer and manager.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank
Target entity description: Frank is the given name of Frank Lampard, the renowned English former professional footballer and manager.
  • A. 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.
  • B. Frank
    Frank is the given name of the British philosopher, mathematician, and economist F. P. Ramsey, known for his influential work in logic, probability, and the foundations of mathematics.
  • C. Frank
    Frank is the given name of the renowned Canadian-American architect Frank Gehry, celebrated for his deconstructivist and sculptural building designs.
  • D. Frank
    Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
  • E. Frank
    Frank is the given first name of the American contemporary street artist and graphic designer Shepard Fairey, known for his iconic "OBEY" and Barack Obama "Hope" posters.
  • 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_69b3453a36908190b95a79a297ca083c completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3551d5d7481908528c2de0a6fda06 completed March 13, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69b5f61fa6d88190b98810b542835817 completed March 14, 2026, 11:58 p.m.
NEDg Description generation batch_69b5f68a994c8190a5b524a4db16b097 completed March 15, 2026, midnight
NED2 Entity disambiguation (via description) batch_69b5f6ece3b08190b880743e9fe4dbad completed March 15, 2026, 12:01 a.m.
Created at: March 12, 2026, 11:29 p.m.