Triple

T19434466
Position Surface form Disambiguated ID Type / Status
Subject Oracle AI Services E486194 entity
Predicate includesService P1393 FINISHED
Object OCI Document Understanding
OCI Document Understanding is an Oracle Cloud Infrastructure AI service that uses machine learning to automatically extract, classify, and analyze information from documents at scale.
E1376033 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: OCI Document Understanding | Statement: [Oracle AI Services, includesService, OCI Document Understanding]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OCI Document Understanding
Context triple: [Oracle AI Services, includesService, OCI Document Understanding]
  • A. Azure Form Recognizer
    Azure Form Recognizer is a cloud-based AI service that uses machine learning to extract structured data, text, and key-value pairs from documents and forms.
  • B. OCRSO
    OCRSO is the acronym for the Office of the Chief Readiness Support Officer, a Department of Homeland Security component responsible for overseeing mission support, logistics, and readiness functions across the department.
  • C. OCR
    OCR is the Office for Civil Rights, a U.S. government agency responsible for enforcing civil rights laws and ensuring equal access and non-discrimination in federally funded programs.
  • D. OCR
    OCR (Oxford, Cambridge and RSA Examinations) is a major UK exam board that designs and administers academic and vocational qualifications, including GCSEs and A Levels.
  • E. LayoutLM
    LayoutLM is a transformer-based document understanding model that jointly leverages text, layout, and visual information to process and analyze scanned documents and forms.
  • 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: OCI Document Understanding
Triple: [Oracle AI Services, includesService, OCI Document Understanding]
Generated description
OCI Document Understanding is an Oracle Cloud Infrastructure AI service that uses machine learning to automatically extract, classify, and analyze information from documents at scale.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: OCI Document Understanding
Target entity description: OCI Document Understanding is an Oracle Cloud Infrastructure AI service that uses machine learning to automatically extract, classify, and analyze information from documents at scale.
  • A. Azure Form Recognizer
    Azure Form Recognizer is a cloud-based AI service that uses machine learning to extract structured data, text, and key-value pairs from documents and forms.
  • B. OCRSO
    OCRSO is the acronym for the Office of the Chief Readiness Support Officer, a Department of Homeland Security component responsible for overseeing mission support, logistics, and readiness functions across the department.
  • C. OCR
    OCR is the Office for Civil Rights, a U.S. government agency responsible for enforcing civil rights laws and ensuring equal access and non-discrimination in federally funded programs.
  • D. OCR
    OCR (Oxford, Cambridge and RSA Examinations) is a major UK exam board that designs and administers academic and vocational qualifications, including GCSEs and A Levels.
  • E. LayoutLM
    LayoutLM is a transformer-based document understanding model that jointly leverages text, layout, and visual information to process and analyze scanned documents and forms.
  • F. None of above. chosen

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_69d8e8d7ad488190a3373045029b0f3b completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6335e8f7881909c8b28886521046e completed April 20, 2026, 2:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0733ddcf108190a92718695326f49d completed May 15, 2026, 2:55 p.m.
NEDg Description generation batch_6a0735dd1b6481909ab747f425f4ec76 completed May 15, 2026, 3:03 p.m.
NED2 Entity disambiguation (via description) batch_6a07367c0edc8190b6cea3c3aa126868 completed May 15, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:37 p.m.