Triple

T14086829
Position Surface form Disambiguated ID Type / Status
Subject Microsoft Office binary formats E339017 entity
Predicate basedOn P98 FINISHED
Object Compound File Binary Format
Compound File Binary Format is a Microsoft-developed container file format that stores multiple streams of data within a single file, commonly used by legacy Microsoft Office documents.
E339017 NE FINISHED

How this triple was built (4 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: Compound File Binary Format | Statement: [Microsoft Office binary formats, basedOn, Compound File Binary Format]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Compound File Binary Format
Context triple: [Microsoft Office binary formats, basedOn, Compound File Binary Format]
  • A. RCFile
    RCFile is a columnar storage file format designed for efficient data processing and querying in Hadoop-based systems.
  • B. Microsoft Office binary formats
    Microsoft Office binary formats are the legacy proprietary file types (such as .doc, .xls, and .ppt) used by earlier versions of Microsoft Office applications for documents, spreadsheets, and presentations.
  • C. Apache Parquet
    Apache Parquet is a columnar storage file format optimized for efficient data compression and query performance in big data processing frameworks such as Apache Hadoop and Apache Spark.
  • D. Maschinelles Austauschformat für Bibliotheken
    Maschinelles Austauschformat für Bibliotheken (MAB) is a German machine-readable data exchange format historically used by libraries to encode and share bibliographic and authority records.
  • E. DjVu
    DjVu is a digital document format designed for efficiently storing and viewing scanned documents, especially those containing a mix of text, line drawings, and photographs, with high compression and fast web viewing.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Compound File Binary Format
Triple: [Microsoft Office binary formats, basedOn, Compound File Binary Format]
Generated description
Compound File Binary Format is a Microsoft-developed container file format that stores multiple streams of data within a single file, commonly used by legacy Microsoft Office documents.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Compound File Binary Format
Target entity description: Compound File Binary Format is a Microsoft-developed container file format that stores multiple streams of data within a single file, commonly used by legacy Microsoft Office documents.
  • A. RCFile
    RCFile is a columnar storage file format designed for efficient data processing and querying in Hadoop-based systems.
  • B. Microsoft Office binary formats chosen
    Microsoft Office binary formats are the legacy proprietary file types (such as .doc, .xls, and .ppt) used by earlier versions of Microsoft Office applications for documents, spreadsheets, and presentations.
  • C. Apache Parquet
    Apache Parquet is a columnar storage file format optimized for efficient data compression and query performance in big data processing frameworks such as Apache Hadoop and Apache Spark.
  • D. Maschinelles Austauschformat für Bibliotheken
    Maschinelles Austauschformat für Bibliotheken (MAB) is a German machine-readable data exchange format historically used by libraries to encode and share bibliographic and authority records.
  • E. DjVu
    DjVu is a digital document format designed for efficiently storing and viewing scanned documents, especially those containing a mix of text, line drawings, and photographs, with high compression and fast web viewing.
  • F. None of above.

Provenance (5 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5edff1b881909ea56dc2429ef2dd completed April 14, 2026, 3:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0a3e55c81909b52f618e9076dd2 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd2ae45108190b1f400e4ae16a258 completed May 7, 2026, 5:58 p.m.
NED2 Entity disambiguation (via description) batch_69fcd3ad7be8819094fc71c9f44fb4cb completed May 7, 2026, 6:02 p.m.
Created at: April 9, 2026, 10:21 p.m.