Triple

T2889733
Position Surface form Disambiguated ID Type / Status
Subject Gnus E59588 entity
Predicate supportsProtocol P203 FINISHED
Object Atom E163311 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: Atom | Statement: [Gnus, supportsProtocol, Atom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Atom
Context triple: [Gnus, supportsProtocol, Atom]
  • A. Atom
    Atom is a free and open-source text and source code editor developed by GitHub, known for its hackability, rich plugin ecosystem, and cross-platform support.
  • B. Atom chosen
    Atom is a family of low-power x86 microprocessors developed by Intel, primarily designed for use in netbooks, embedded systems, and energy-efficient devices.
  • C. Atomico
    Atomico is a London-based venture capital firm known for investing in innovative technology startups, founded by Skype co-creator Niklas Zennström.
  • D. Les Atomes
    Les Atomes is a seminal scientific work by Jean Perrin that helped establish the reality of atoms through experimental evidence and clear popular exposition of atomic theory.
  • E. Atombaupreis
    The Atombaupreis was a German scientific award recognizing outstanding contributions to nuclear physics and atomic research.
  • 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_69ab4ac739188190a112f42a5a69c951 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abe04a68ac8190aaeafe52138beb74 completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b03179d7448190bcdbea164856aaa2 completed March 10, 2026, 2:58 p.m.
Created at: March 6, 2026, 10:04 p.m.