Triple

T10329802
Position Surface form Disambiguated ID Type / Status
Subject Acid3 E242845 entity
Predicate testsAspect P93446 FINISHED
Object DOM Level 3 E857097 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: DOM Level 3 | Statement: [Acid3, testsAspect, DOM Level 3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DOM Level 3
Context triple: [Acid3, testsAspect, DOM Level 3]
  • A. DOM Level 3 chosen
    DOM Level 3 is a W3C specification that extends the Document Object Model with advanced features for manipulating and interacting with structured documents like HTML and XML.
  • B. DOM Level 2
    DOM Level 2 is a W3C specification that extends the Document Object Model with standardized interfaces for events, traversal, ranges, and improved document manipulation in web browsers.
  • C. Selectors Level 3
    Selectors Level 3 is a W3C CSS specification that defines the syntax and behavior of selectors used to target elements in web documents for styling and scripting.
  • D. Selectors Level 4
    Selectors Level 4 is a W3C CSS specification that extends and refines the set of selectors available to web authors for targeting elements in HTML and XML documents.
  • E. DOM
    The Document Object Model (DOM) is a platform- and language-neutral interface that represents structured documents like HTML and XML as a tree of objects, enabling programs and scripts to dynamically access and update their content and structure.
  • 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_69d4dfc1b0488190ac04da58a4987da0 completed April 7, 2026, 10:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fb69410c81909b33e44a04ab77d9 completed April 9, 2026, 7:18 p.m.
Created at: April 6, 2026, 11:52 a.m.