Triple

T22690138
Position Surface form Disambiguated ID Type / Status
Subject A10BJ05 E561028 entity
Predicate secondAndThirdCharactersMeaning P143690 FINISHED
Object 10 = Drugs used in diabetes LITERAL FINISHED

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: 10 = Drugs used in diabetes | Statement: [A10BJ05, secondAndThirdCharactersMeaning, 10 = Drugs used in diabetes]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: secondAndThirdCharactersMeaning
Context triple: [A10BJ05, secondAndThirdCharactersMeaning, 10 = Drugs used in diabetes]
  • A. associatedCharacterMeaning
    Indicates that there is a relationship between a character and the meaning, interpretation, or concept that this character is intended to represent.
  • B. secondPartMeaning
    Indicates that something represents the latter or subsequent portion of a larger whole in terms of its meaning or semantic content.
  • C. codeThirdDigitMeaning chosen
    Indicates how the third digit in a given code specifies or determines a particular meaning, category, or attribute within that coding system.
  • D. digitMeaning
    Indicates that a particular digit symbol is associated with a specific numerical value or conceptual meaning.
  • E. hasLastThreeLettersMeaning
    Indicates that the last three letters of one entity (typically a word or string) together form a meaningful unit or have a specific semantic significance.
  • F. None of above.

Provenance (3 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789a1fd08190bce5fa0babe695d3 completed April 29, 2026, 3:18 a.m.
PD Predicate disambiguation batch_69ee62b2259c819091ed1387a748b9f3 completed April 26, 2026, 7:08 p.m.
Created at: April 17, 2026, 3:13 p.m.