Triple

T11037022
Position Surface form Disambiguated ID Type / Status
Subject Heroes E260911 entity
Predicate hasMainCharacter P1183 FINISHED
Object Matt Parkman
Matt Parkman is a fictional police officer with telepathic abilities in the television series "Heroes."
E907122 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: Matt Parkman | Statement: [Heroes, hasMainCharacter, Matt Parkman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Parkman
Context triple: [Heroes, hasMainCharacter, Matt Parkman]
  • A. Chauncey Goss
    Chauncey Goss is an American public official and policy analyst known for his work in fiscal policy and water management in Florida.
  • B. Louis Tully
    Louis Tully is a nerdy, well-meaning accountant and neighbor of Dana Barrett who becomes a comedic, possessed pawn of Gozer in the Ghostbusters films.
  • C. Charles Grigsby
    Charles Grigsby is an American singer best known for reaching the finals on the second season of the television talent competition American Idol.
  • D. Henry McHenry
    Henry McHenry is an American paleoanthropologist and professor known for his research on human evolution, particularly the biomechanics and locomotion of early hominins.
  • E. Franklin Keeler
    Franklin Keeler was the founder of the Times Union newspaper.
  • 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: Matt Parkman
Triple: [Heroes, hasMainCharacter, Matt Parkman]
Generated description
Matt Parkman is a fictional police officer with telepathic abilities in the television series "Heroes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Matt Parkman
Target entity description: Matt Parkman is a fictional police officer with telepathic abilities in the television series "Heroes."
  • A. Chauncey Goss
    Chauncey Goss is an American public official and policy analyst known for his work in fiscal policy and water management in Florida.
  • B. Louis Tully
    Louis Tully is a nerdy, well-meaning accountant and neighbor of Dana Barrett who becomes a comedic, possessed pawn of Gozer in the Ghostbusters films.
  • C. Charles Grigsby
    Charles Grigsby is an American singer best known for reaching the finals on the second season of the television talent competition American Idol.
  • D. Henry McHenry
    Henry McHenry is an American paleoanthropologist and professor known for his research on human evolution, particularly the biomechanics and locomotion of early hominins.
  • E. Franklin Keeler
    Franklin Keeler was the founder of the Times Union newspaper.
  • 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_69d6aa979bdc8190bf0e79104cc098c1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797e9e3fc8190802195ac9fcb8e28 completed April 9, 2026, 12:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4419a91b08190a55c7f874a3df0fe completed April 19, 2026, 2:44 a.m.
NEDg Description generation batch_69e44c0606408190819b9d3fd58f818f completed April 19, 2026, 3:29 a.m.
NED2 Entity disambiguation (via description) batch_69e4510dc55081908f89aab15726b2a8 completed April 19, 2026, 3:50 a.m.
Created at: April 8, 2026, 9:25 p.m.