Triple

T505899
Position Surface form Disambiguated ID Type / Status
Subject Moby-Dick E10500 entity
Predicate hasCharacter P2308 FINISHED
Object Flask
Flask is a minor but tough and pugnacious third mate aboard the whaling ship Pequod in Herman Melville’s novel "Moby-Dick."
E62710 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: Flask | Statement: [Moby-Dick, hasCharacter, Flask]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flask
Context triple: [Moby-Dick, hasCharacter, Flask]
  • A. Flask
    Flask is a lightweight, flexible Python micro web framework designed for building web applications and APIs with minimal boilerplate.
  • B. Django
    Django is a high-level Python web framework that encourages rapid development and clean, pragmatic design for building secure, scalable web applications.
  • C. FastAPI
    FastAPI is a modern, high-performance Python framework for building APIs with automatic interactive documentation and type hint–driven validation.
  • D. Express.js
    Express.js is a minimalist and flexible Node.js web application framework used to build APIs and server-side applications.
  • E. PyPy
    PyPy is a high-performance alternative Python interpreter featuring a Just-In-Time (JIT) compiler designed to significantly speed up the execution of Python programs.
  • 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: Flask
Triple: [Moby-Dick, hasCharacter, Flask]
Generated description
Flask is a minor but tough and pugnacious third mate aboard the whaling ship Pequod in Herman Melville’s novel "Moby-Dick."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Flask
Target entity description: Flask is a minor but tough and pugnacious third mate aboard the whaling ship Pequod in Herman Melville’s novel "Moby-Dick."
  • A. Flask
    Flask is a lightweight, flexible Python micro web framework designed for building web applications and APIs with minimal boilerplate.
  • B. Django
    Django is a high-level Python web framework that encourages rapid development and clean, pragmatic design for building secure, scalable web applications.
  • C. FastAPI
    FastAPI is a modern, high-performance Python framework for building APIs with automatic interactive documentation and type hint–driven validation.
  • D. Express.js
    Express.js is a minimalist and flexible Node.js web application framework used to build APIs and server-side applications.
  • E. PyPy
    PyPy is a high-performance alternative Python interpreter featuring a Just-In-Time (JIT) compiler designed to significantly speed up the execution of Python programs.
  • 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_69a2e848adf881908e5e04f7af030093 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f14b2acc8190818e8a53eac69c54 completed Feb. 28, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a48a7d47cc8190be1741f95f967f25 completed March 1, 2026, 6:50 p.m.
NEDg Description generation batch_69a48ae58a288190b4fa3e7a052477ca completed March 1, 2026, 6:52 p.m.
NED2 Entity disambiguation (via description) batch_69a48b35abe881909029c02557da0819 completed March 1, 2026, 6:53 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.