Triple

T17560899
Position Surface form Disambiguated ID Type / Status
Subject WKB E427693 entity
Predicate relatedStandard P37 FINISHED
Object Well-Known Text NE NERFINISHED

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: Well-Known Text | Statement: [WKB, relatedStandard, Well-Known Text]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Well-Known Text
Context triple: [WKB, relatedStandard, Well-Known Text]
  • A. WKT chosen
    WKT (Well-Known Text) is a text-based markup language used to represent vector geometry objects such as points, lines, and polygons in geographic information systems.
  • B. BSON
    BSON is a binary-encoded serialization format commonly used by MongoDB to store and transfer structured data efficiently while supporting additional data types beyond those in JSON.
  • C. CBOR
    CBOR (Concise Binary Object Representation) is a compact, schema-less binary data serialization format designed for efficient, small-footprint data interchange, especially in constrained environments like IoT.
  • D. StAX
    StAX (Streaming API for XML) is a Java-based pull-parsing API that enables efficient, forward-only, stream-oriented processing of XML documents.
  • E. Rich Text Format
    Rich Text Format (RTF) is a cross-platform document file format developed by Microsoft that preserves basic text formatting and structure while remaining readable by many word processors.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e456267e208190a1238fbe1a535bb0 completed April 19, 2026, 4:12 a.m.
Created at: April 10, 2026, 5:50 a.m.