Triple

T20663658
Position Surface form Disambiguated ID Type / Status
Subject Lawrence Block E507824 entity
Predicate notableSeries P3199 FINISHED
Object Keller
Keller is a fictional hitman and stamp-collecting antihero who stars in Lawrence Block’s popular series of crime novels and short stories.
 E1443791 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: Keller | Statement: [Lawrence Block, notableSeries, Keller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keller
Context triple: [Lawrence Block, notableSeries, Keller]
  • A. Keller
    Keller is a suburban city in the Dallas–Fort Worth metropolitan area known for its family-friendly neighborhoods and strong public schools.
  • B. Keller
    Keller is a given name that can function as either a surname-derived first name or a standalone personal name in English-speaking contexts.
  • C. Keller
    Keller is the surname of Helen Keller, the renowned American author and disability rights advocate who was both deaf and blind.
  • D. Kelson
    Kelson is a residential suburb located in the city of Lower Hutt in the Wellington region of New Zealand.
  • E. Krier
    Krier is a surname most notably associated with Leon Krier, a Luxembourgish architect and urban planner known for his advocacy of traditional urbanism and criticism of modernist architecture.
  • 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: Keller
Triple: [Lawrence Block, notableSeries, Keller]
Generated description
Keller is a fictional hitman and stamp-collecting antihero who stars in Lawrence Block’s popular series of crime novels and short stories.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keller
Target entity description: Keller is a fictional hitman and stamp-collecting antihero who stars in Lawrence Block’s popular series of crime novels and short stories.
  • A. Keller
    Keller is the surname of Helen Keller, the renowned American author and disability rights advocate who was both deaf and blind.
  • B. Keller
    Keller is a suburban city in the Dallas–Fort Worth metropolitan area known for its family-friendly neighborhoods and strong public schools.
  • C. Keller
    Keller is a given name that can function as either a surname-derived first name or a standalone personal name in English-speaking contexts.
  • D. Kelson
    Kelson is a residential suburb located in the city of Lower Hutt in the Wellington region of New Zealand.
  • E. Krier
    Krier is a surname most notably associated with Leon Krier, a Luxembourgish architect and urban planner known for his advocacy of traditional urbanism and criticism of modernist architecture.
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2f4872481908858eb88ce89dd47 completed April 20, 2026, 11:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08cd5d0da481909eebd69b8b314503 completed May 16, 2026, 8:02 p.m.
NEDg Description generation batch_6a08d175206c8190b119bb1a2d06462f completed May 16, 2026, 8:20 p.m.
NED2 Entity disambiguation (via description) batch_6a08d28e02fc8190ab694673156ab0c0 completed May 16, 2026, 8:24 p.m.
Created at: April 16, 2026, 11:44 a.m.