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.