Triple

T5552785
Position Surface form Disambiguated ID Type / Status
Subject Denver, Colorado E145565 entity
Predicate mayor P185 FINISHED
Object Mike Johnston
Mike Johnston is an American educator, former Colorado state senator, and Democratic politician who became mayor of Denver.
 E530203 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: Mike Johnston | Statement: [Denver, Colorado, mayor, Mike Johnston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mike Johnston
Context triple: [Denver, Colorado, mayor, Mike Johnston]
  • A. Brad Oscar
    Brad Oscar is an American stage actor and singer best known for his comedic roles in major Broadway musicals, including his acclaimed work in Mel Brooks’s The Producers.
  • B. Jack Cummings
    Jack Cummings was an American film producer best known for his work on classic MGM musicals in the mid-20th century.
  • C. Justin E. Driscoll
    Justin E. Driscoll is an American energy executive who leads the New York Power Authority, the nation’s largest state-owned electric utility.
  • D. Brian James
    Brian James is a rock guitarist best known as a founding member of the pioneering punk band The Damned.
  • E. Michael Schultz
    Michael Schultz is an American film and television director best known for his influential work on 1970s comedies and dramas, including the cult classic "Car Wash."
  • 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: Mike Johnston
Triple: [Denver, Colorado, mayor, Mike Johnston]
Generated description
Mike Johnston is an American educator, former Colorado state senator, and Democratic politician who became mayor of Denver.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mike Johnston
Target entity description: Mike Johnston is an American educator, former Colorado state senator, and Democratic politician who became mayor of Denver.
  • A. Brad Oscar
    Brad Oscar is an American stage actor and singer best known for his comedic roles in major Broadway musicals, including his acclaimed work in Mel Brooks’s The Producers.
  • B. Jack Cummings
    Jack Cummings was an American film producer best known for his work on classic MGM musicals in the mid-20th century.
  • C. Justin E. Driscoll
    Justin E. Driscoll is an American energy executive who leads the New York Power Authority, the nation’s largest state-owned electric utility.
  • D. Brian James
    Brian James is a rock guitarist best known as a founding member of the pioneering punk band The Damned.
  • E. Michael Schultz
    Michael Schultz is an American film and television director best known for his influential work on 1970s comedies and dramas, including the cult classic "Car Wash."
  • 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_69c008fb879c81909f5bfa56fadc1d46 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01ff872bc81908e14776f7ba4154e completed March 22, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0283878d88190ac60064e604aa002 completed March 22, 2026, 5:34 p.m.
NEDg Description generation batch_69c0407824dc81908bc6a9662e0dbe7a completed March 22, 2026, 7:18 p.m.
NED2 Entity disambiguation (via description) batch_69c04141ea408190aba1463d56ad6b7d completed March 22, 2026, 7:21 p.m.
Created at: March 22, 2026, 3:35 p.m.