Triple

T20389375
Position Surface form Disambiguated ID Type / Status
Subject Moonlighting E498044 entity
Predicate character P662 FINISHED
Object David Addison Jr.
David Addison Jr. is the wisecracking, charismatic private detective played by Bruce Willis on the 1980s television series "Moonlighting."
E1428720 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: David Addison Jr. | Statement: [Moonlighting, character, David Addison Jr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Addison Jr.
Context triple: [Moonlighting, character, David Addison Jr.]
  • A. Bruce Douglas Johnson
    Bruce Douglas Johnson is a cinematographer best known for his work on the stoner comedy film "Harold & Kumar Go to White Castle."
  • B. Alex Johnson
    Alex Johnson is a musician best known as a member of the Canadian rock band Big Sugar.
  • C. Frank M. Johnson Jr.
    Frank M. Johnson Jr. was a prominent U.S. federal judge known for his pivotal civil rights rulings that helped dismantle segregation in the American South.
  • D. Bill Pierce
    Bill Pierce is the husband of acclaimed American novelist Celeste Ng.
  • E. John Sullivan
    John Sullivan was a celebrated British television writer best known for creating the classic sitcom "Only Fools and Horses."
  • 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: David Addison Jr.
Triple: [Moonlighting, character, David Addison Jr.]
Generated description
David Addison Jr. is the wisecracking, charismatic private detective played by Bruce Willis on the 1980s television series "Moonlighting."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Addison Jr.
Target entity description: David Addison Jr. is the wisecracking, charismatic private detective played by Bruce Willis on the 1980s television series "Moonlighting."
  • A. Bruce Douglas Johnson
    Bruce Douglas Johnson is a cinematographer best known for his work on the stoner comedy film "Harold & Kumar Go to White Castle."
  • B. Alex Johnson
    Alex Johnson is a musician best known as a member of the Canadian rock band Big Sugar.
  • C. Frank M. Johnson Jr.
    Frank M. Johnson Jr. was a prominent U.S. federal judge known for his pivotal civil rights rulings that helped dismantle segregation in the American South.
  • D. Bill Pierce
    Bill Pierce is the husband of acclaimed American novelist Celeste Ng.
  • E. John Sullivan
    John Sullivan was a celebrated British television writer best known for creating the classic sitcom "Only Fools and Horses."
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790e65a081909832855758fffd14 completed April 20, 2026, 7:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08762218448190a3339dbbe0f23962 completed May 16, 2026, 1:50 p.m.
NEDg Description generation batch_6a087754af1481909a8ffa042aad2f42 completed May 16, 2026, 1:55 p.m.
NED2 Entity disambiguation (via description) batch_6a0877dcf9548190bd42db7a54aea824 completed May 16, 2026, 1:57 p.m.
Created at: April 16, 2026, 11:28 a.m.