Triple

T2358502
Position Surface form Disambiguated ID Type / Status
Subject Flying Pencil E47212 entity
Predicate notableVariant P4680 FINISHED
Object Do 17M
The Do 17M was a German Dornier Do 17 "Flying Pencil" bomber variant developed in the late 1930s with improved performance and payload capacity for Luftwaffe operations.
 E258007 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: Do 17M | Statement: [Flying Pencil, notableVariant, Do 17M]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Do 17M
Context triple: [Flying Pencil, notableVariant, Do 17M]
  • A. M1
    M1 is a boat line that operates as part of Geneva’s public transport network, providing passenger service across the city’s waters.
  • B. M15
    M15 is a New York City MTA bus route that runs along First and Second Avenues in Manhattan, connecting the East Side to Lower Manhattan and the South Ferry area.
  • C. B17
    B17 is a New York City bus route that operates in Brooklyn, connecting the Canarsie neighborhood with other parts of the borough.
  • D. Mc
    Mc is a Gaelic patronymic prefix meaning "son of," commonly found in Scottish and Irish surnames.
  • E. M
    M is a functional data mashup and query language used in Microsoft Power BI and related tools for data transformation and preparation.
  • 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: Do 17M
Triple: [Flying Pencil, notableVariant, Do 17M]
Generated description
The Do 17M was a German Dornier Do 17 "Flying Pencil" bomber variant developed in the late 1930s with improved performance and payload capacity for Luftwaffe operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Do 17M
Target entity description: The Do 17M was a German Dornier Do 17 "Flying Pencil" bomber variant developed in the late 1930s with improved performance and payload capacity for Luftwaffe operations.
  • A. M1
    M1 is a boat line that operates as part of Geneva’s public transport network, providing passenger service across the city’s waters.
  • B. M15
    M15 is a New York City MTA bus route that runs along First and Second Avenues in Manhattan, connecting the East Side to Lower Manhattan and the South Ferry area.
  • C. B17
    B17 is a New York City bus route that operates in Brooklyn, connecting the Canarsie neighborhood with other parts of the borough.
  • D. Mc
    Mc is a Gaelic patronymic prefix meaning "son of," commonly found in Scottish and Irish surnames.
  • E. M
    M is a functional data mashup and query language used in Microsoft Power BI and related tools for data transformation and preparation.
  • 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_69a88a1a4a6081908645b0f2914521ab completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc71f767481908dfa9be209ea3c5a completed March 7, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9638ef948190adf945aba42fac76 completed March 9, 2026, 9:43 a.m.
NEDg Description generation batch_69ae96fc0b508190b1da6aa41cddc488 completed March 9, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_69ae977e539c81909cef638cc61e5ec1 completed March 9, 2026, 9:48 a.m.
Created at: March 4, 2026, 7:55 p.m.