Triple

T10329894
Position Surface form Disambiguated ID Type / Status
Subject Ian Hickson E242847 entity
Predicate knownFor P22 FINISHED
Object Acid2 test E242841 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: Acid2 test | Statement: [Ian Hickson, knownFor, Acid2 test]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Acid2 test
Context triple: [Ian Hickson, knownFor, Acid2 test]
  • A. Acid2 test chosen
    The Acid2 test is a web standards compliance test designed to reveal flaws in web browser rendering engines by using a complex, precisely specified visual layout.
  • B. Acid3 test
    The Acid3 test is a web browser benchmark designed to check compliance with web standards, particularly those related to the Document Object Model (DOM), JavaScript, and rendering.
  • C. Acid2
    Acid2 is a web browser test created to check standards compliance in CSS and HTML rendering engines.
  • D. Acid tests
    Acid tests are a series of web browser benchmark tests designed to check compliance with various web standards and rendering correctness.
  • E. Acid3
    Acid3 is a web standards compliance test designed to assess how well web browsers handle modern web technologies like DOM, JavaScript, and CSS.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7fb77348190ac8ff887f6f03450 completed April 7, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7504679ec8190926d2c5016653cea completed April 9, 2026, 7:07 a.m.
Created at: April 6, 2026, 11:52 a.m.