Triple

T3310839
Position Surface form Disambiguated ID Type / Status
Subject Lance Reddick E69566 entity
Predicate characterPortrayed P1507 FINISHED
Object Irvin Irving
Irvin Irving is a high-ranking, politically savvy LAPD official in the Bosch crime drama series, portrayed by actor Lance Reddick.
 E346976 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: Irvin Irving | Statement: [Lance Reddick, characterPortrayed, Irvin Irving]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Irvin Irving
Context triple: [Lance Reddick, characterPortrayed, Irvin Irving]
  • A. Everett Irving
    Everett Irving is one of the children of acclaimed American novelist John Irving.
  • B. Roger Brown
    Roger Brown was an influential American social psychologist and linguist known for his pioneering research on language acquisition and the social psychology of language.
  • C. Roger Brown
    Roger Brown was a professional basketball player best known for his scoring and rebounding in the American Basketball Association during the 1970s.
  • D. Milt Franklyn
    Milt Franklyn was an American composer and arranger best known for scoring numerous Warner Bros. Looney Tunes and Merrie Melodies cartoons in the mid-20th century.
  • E. Earl Richey Jones
    Earl Richey Jones is a screenwriter best known for co-writing the 1999 science fiction comedy film "Galaxy Quest."
  • 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: Irvin Irving
Triple: [Lance Reddick, characterPortrayed, Irvin Irving]
Generated description
Irvin Irving is a high-ranking, politically savvy LAPD official in the Bosch crime drama series, portrayed by actor Lance Reddick.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Irvin Irving
Target entity description: Irvin Irving is a high-ranking, politically savvy LAPD official in the Bosch crime drama series, portrayed by actor Lance Reddick.
  • A. Everett Irving
    Everett Irving is one of the children of acclaimed American novelist John Irving.
  • B. Roger Brown
    Roger Brown was an influential American social psychologist and linguist known for his pioneering research on language acquisition and the social psychology of language.
  • C. Roger Brown
    Roger Brown was a professional basketball player best known for his scoring and rebounding in the American Basketball Association during the 1970s.
  • D. Milt Franklyn
    Milt Franklyn was an American composer and arranger best known for scoring numerous Warner Bros. Looney Tunes and Merrie Melodies cartoons in the mid-20th century.
  • E. Earl Richey Jones
    Earl Richey Jones is a screenwriter best known for co-writing the 1999 science fiction comedy film "Galaxy Quest."
  • 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_69ad859f218081909458d2cebbf57565 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0ec80508190baa78435b983b7b5 completed March 8, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3f0d52081908bbade5e514f17d1 completed March 12, 2026, 5:12 p.m.
NEDg Description generation batch_69b2fa6edd6c8190a398e622c1c8600c completed March 12, 2026, 5:39 p.m.
NED2 Entity disambiguation (via description) batch_69b31413fa2481908a52237df05e6fe6 completed March 12, 2026, 7:29 p.m.
Created at: March 8, 2026, 3:11 p.m.