Triple

T20561871
Position Surface form Disambiguated ID Type / Status
Subject Jonathan Brandis E504861 entity
Predicate portrayed P1668 FINISHED
Object Matthew
Matthew is a fictional character played by American actor Jonathan Brandis, best known for his roles in 1990s film and television.
E1438620 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: Matthew | Statement: [Jonathan Brandis, portrayed, Matthew]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew
Context triple: [Jonathan Brandis, portrayed, Matthew]
  • A. John
    John is the given name of John D. Rockefeller, the American industrialist and philanthropist who founded Standard Oil and became one of the wealthiest individuals in history.
  • B. John
    John Vassall Jr. was a British civil servant who became notorious as a Soviet spy during the Cold War.
  • C. John
    John is the given name of John W. Mauchly, the American physicist and co-inventor of the ENIAC computer.
  • D. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • E. John
    John is the first name of American actor and musician John Stamos, best known for his role as Uncle Jesse on the television series "Full House."
  • 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: Matthew
Triple: [Jonathan Brandis, portrayed, Matthew]
Generated description
Matthew is a fictional character played by American actor Jonathan Brandis, best known for his roles in 1990s film and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Matthew
Target entity description: Matthew is a fictional character played by American actor Jonathan Brandis, best known for his roles in 1990s film and television.
  • A. Matthew
    Matthew is a fictional character portrayed by American actor Michael Pitt, best known from the film "The Dreamers."
  • B. Matthew
    Matthew is the given first name of American actor Ryan Phillippe, known for films like "Cruel Intentions" and "Crash."
  • C. Matthew
    Matthew is a person known primarily as Lisa's romantic partner.
  • D. Matthew
    Matthew is a character in the 2017 film "Albion," a fantasy adventure story involving a young girl transported to a magical world.
  • E. Matthew
    Matthew is the central protagonist of the film "Wicker Park," whose obsessive search for a lost love drives the movie’s intricate romantic mystery.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a79ec10481909740eb6a08ae2658 completed April 20, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08acdac8008190a7a61d46f7041cf4 completed May 16, 2026, 5:43 p.m.
NEDg Description generation batch_6a08ada4ef648190982235ebe059a9c5 completed May 16, 2026, 5:47 p.m.
NED2 Entity disambiguation (via description) batch_6a08aeaf2be88190bac218c7de1544fc completed May 16, 2026, 5:51 p.m.
Created at: April 16, 2026, 11:39 a.m.