Triple

T521293
Position Surface form Disambiguated ID Type / Status
Subject Denis Diderot E10822 entity
Predicate notableWork P4 FINISHED
Object Encyclopédie E4820 NE FINISHED

How this triple was built (2 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: Encyclopédie | Statement: [Denis Diderot, notableWork, Encyclopédie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Encyclopédie
Context triple: [Denis Diderot, notableWork, Encyclopédie]
  • A. Encyclopédie chosen
    The Encyclopédie was an influential 18th-century French reference work edited by Denis Diderot and Jean le Rond d’Alembert that sought to compile and disseminate Enlightenment knowledge, science, and philosophy.
  • B. Encyclopaedia Britannica
    Encyclopaedia Britannica is a long-standing, highly respected general knowledge reference work first published in the 18th century and now available in both print and digital formats.
  • C. Le Siècle
    Le Siècle was a prominent 19th-century French newspaper known for publishing major literary works and influencing public opinion in France.
  • D. Wikisource
    Wikisource is a free online digital library of public domain and freely licensed texts that anyone can read and help transcribe.
  • E. Codex
    Codex is an AI system developed by OpenAI that translates natural language into code and powers tools like GitHub Copilot.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a2e84b16c4819088d284c47c3a7968 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f1a1817c8190a6cc8f423071d3ad completed Feb. 28, 2026, 1:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4a7005ff08190870f19550ede4ee3 completed March 1, 2026, 8:52 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.