Triple

T30644176
Position Surface form Disambiguated ID Type / Status
Subject Canon EOS M6 Mark II E780072 entity
Predicate rawFormat P109452 FINISHED
Object Canon CR3 RAW
Canon CR3 RAW is Canon’s modern compressed RAW image file format that preserves high-quality sensor data while reducing file size for efficient storage and processing.
 E1923531 NE FINISHED

How this triple was built (3 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: Canon CR3 RAW | Statement: [Canon EOS M6 Mark II, rawFormat, Canon CR3 RAW]
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: Canon CR3 RAW
Triple: [Canon EOS M6 Mark II, rawFormat, Canon CR3 RAW]
Generated description
Canon CR3 RAW is Canon’s modern compressed RAW image file format that preserves high-quality sensor data while reducing file size for efficient storage and processing.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: rawFormat
Context triple: [Canon EOS M6 Mark II, rawFormat, Canon CR3 RAW]
  • A. openFormat
    Indicates that an entity is presented or made available in a format that is open, accessible, and not restricted by proprietary constraints.
  • B. usedFormat chosen
    Indicates that one entity employs or applies a particular format or representation in relation to another entity.
  • C. packageFormat
    Indicates the format or type in which a package is structured, encoded, or delivered.
  • D. format
    Indicates the specific arrangement, structure, or presentation style in which something is organized or expressed.
  • E. temporaryFormat
    Indicates a relationship where something is given a non-permanent or provisional format, structure, or representation intended only for temporary use.
  • F. None of above.

Provenance (6 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_69f224a50ebc81909b961a94c7f66b12 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f68a58cd808190bc1cdaa106291084 completed May 2, 2026, 11:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2863f7d0ac8190b9a4c7c705e23812 completed June 9, 2026, 7:05 p.m.
NEDg Description generation batch_6a286808a0f08190bafb3042e599b668 completed June 9, 2026, 7:22 p.m.
NED2 Entity disambiguation (via description) batch_6a286896d8e48190879f6acc0ed79877 completed June 9, 2026, 7:25 p.m.
PD Predicate disambiguation batch_69f67e448a9c8190b591374d98799fe3 completed May 2, 2026, 10:44 p.m.
Created at: April 29, 2026, 8:29 p.m.