Triple

T15071975
Position Surface form Disambiguated ID Type / Status
Subject The Narrows E379898 entity
Predicate featuresCharacter P626 FINISHED
Object Robert Backus
Robert Backus is a fictional character featured in the crime novel "The Narrows" by Michael Connelly.
E1134755 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: Robert Backus | Statement: [The Narrows, featuresCharacter, Robert Backus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Backus
Context triple: [The Narrows, featuresCharacter, Robert Backus]
  • A. Robert Vinton
    Robert Vinton is one of the children of American pop singer Bobby Vinton, who rose to fame in the 1960s and 1970s.
  • B. Allan Kayser
    Allan Kayser is an American actor best known for playing Bubba Higgins on the sitcom "Mama’s Family."
  • C. Michael Goguen
    Michael Goguen is an American animation producer and director best known for his work on numerous superhero and action-oriented animated television series.
  • D. Fred M. Wilcox
    Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
  • E. Bernard A. Galler
    Bernard A. Galler was an American computer scientist known for his contributions to programming languages and software systems, as well as his leadership roles in professional computing organizations.
  • 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: Robert Backus
Triple: [The Narrows, featuresCharacter, Robert Backus]
Generated description
Robert Backus is a fictional character featured in the crime novel "The Narrows" by Michael Connelly.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robert Backus
Target entity description: Robert Backus is a fictional character featured in the crime novel "The Narrows" by Michael Connelly.
  • A. Robert Vinton
    Robert Vinton is one of the children of American pop singer Bobby Vinton, who rose to fame in the 1960s and 1970s.
  • B. Allan Kayser
    Allan Kayser is an American actor best known for playing Bubba Higgins on the sitcom "Mama’s Family."
  • C. Michael Goguen
    Michael Goguen is an American animation producer and director best known for his work on numerous superhero and action-oriented animated television series.
  • D. Fred M. Wilcox
    Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
  • E. Bernard A. Galler
    Bernard A. Galler was an American computer scientist known for his contributions to programming languages and software systems, as well as his leadership roles in professional computing organizations.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dff7f86df48190b3a2cf441fefb477 completed April 15, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fea5cff69c8190b6252509c1aa7ebb completed May 9, 2026, 3:11 a.m.
NEDg Description generation batch_69fea6bf2558819082fc91fe8df6f3f5 completed May 9, 2026, 3:15 a.m.
NED2 Entity disambiguation (via description) batch_69fea8018a088190b6eba72a7e6196b2 completed May 9, 2026, 3:20 a.m.
Created at: April 10, 2026, 3:02 a.m.