Triple
T32400507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | YOSEMITE |
E827934
|
entity |
| Predicate | evaluatesCondition |
P174991
|
FINISHED |
| Object | diabetic macular edema |
—
|
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: diabetic macular edema | Statement: [YOSEMITE, evaluatesCondition, diabetic macular edema]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evaluatesCondition Context triple: [YOSEMITE, evaluatesCondition, diabetic macular edema]
-
A.
evaluatesAs
Indicates that one entity is judged, interpreted, or assessed as having a particular value, role, or classification in relation to another.
-
B.
hasCondition
Indicates that an entity possesses, experiences, or is affected by a particular condition or state.
-
C.
containsCondition
Indicates that one entity includes, embodies, or is associated with a particular condition.
-
D.
variableCondition
Indicates that a variable is subject to a specific state, constraint, or requirement that must hold for a given context or operation.
-
E.
canCondition
Indicates that one entity has the capability or potential to impose, apply, or bring about a particular condition on another entity or situation.
- F. None of above. chosen
Provenance (4 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_69f34919342c8190a4c3bf35a90d4e58 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6cd9bae8c8190b528641499162a75 |
completed | May 3, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
| PDg | Predicate description generation | batch_69f6cd119cac8190a0b3ebe8b9c742c2 |
completed | May 3, 2026, 4:20 a.m. |
Created at: May 1, 2026, 12:52 a.m.