Triple

T13858032
Position Surface form Disambiguated ID Type / Status
Subject Desktop Underwriter E333113 entity
Predicate abbreviation P43 FINISHED
Object DU
DU is an automated underwriting system developed by Fannie Mae that evaluates mortgage loan applications and assesses borrower credit risk.
 E1066971 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: DU | Statement: [Desktop Underwriter, abbreviation, DU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DU
Context triple: [Desktop Underwriter, abbreviation, DU]
  • A. DU
    DU is a premier public central university in India, renowned for its diverse academic programs and large collegiate system based in New Delhi.
  • B. DU
    DU is the vehicle registration code used on license plates for the German city of Duisburg.
  • C. DU
    DU is the commonly used abbreviation for the University of Dhaka, a leading public research university in Bangladesh.
  • D. DU
    DU is the commonly used abbreviation for the University of Denver, particularly associated with its Denver Pioneers athletic programs.
  • E. Du
    Du is a Chinese surname historically borne by notable figures such as the Tang dynasty poet Du Fu.
  • 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: DU
Triple: [Desktop Underwriter, abbreviation, DU]
Generated description
DU is an automated underwriting system developed by Fannie Mae that evaluates mortgage loan applications and assesses borrower credit risk.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DU
Target entity description: DU is an automated underwriting system developed by Fannie Mae that evaluates mortgage loan applications and assesses borrower credit risk.
  • A. DU
    DU is a premier public central university in India, renowned for its diverse academic programs and large collegiate system based in New Delhi.
  • B. DU
    DU is the vehicle registration code used on license plates for the German city of Duisburg.
  • C. DU
    DU is the commonly used abbreviation for the University of Dhaka, a leading public research university in Bangladesh.
  • D. DU
    DU is the commonly used abbreviation for the University of Denver, particularly associated with its Denver Pioneers athletic programs.
  • E. Du
    Du is a Chinese surname historically borne by notable figures such as the Tang dynasty poet Du Fu.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02dc9f488190b7181dcb7e304632 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0fb7c3c819081fc6f89aa17d6af completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c2c711948190ac614291592a7e03 completed May 3, 2026, 9:48 p.m.
NED2 Entity disambiguation (via description) batch_69f7c36f28b48190b734a9e5e7ae39b9 completed May 3, 2026, 9:51 p.m.
Created at: April 9, 2026, 10:14 p.m.