Triple
T18021146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pulmonary veins |
E431118
|
entity |
| Predicate | oxygenationLevelOfBlood |
P129469
|
FINISHED |
| Object | High |
—
|
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: High | Statement: [Pulmonary veins, oxygenationLevelOfBlood, High]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oxygenationLevelOfBlood Context triple: [Pulmonary veins, oxygenationLevelOfBlood, High]
-
A.
oxygenationIndicator
Indicates that something serves as a marker or measure of the presence, level, or status of oxygenation in a system or process.
-
B.
oxygenValueApprox
Indicates that the oxygen value of an entity is approximately equal to a specified reference value, within an acceptable margin of error.
-
C.
oxygenPhysiology
Indicates the physiological processes, functions, or effects involving oxygen in an organism.
-
D.
usedSupplementaryOxygen
Indicates that an entity received or utilized additional oxygen support beyond normal atmospheric breathing, typically via medical equipment.
-
E.
bloodStatus
Indicates the classification of an entity based on the type or purity of its blood or lineage.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c299c48190b0cceecf77cb6de9 |
completed | April 19, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_69e3f904b8048190add43883cd7cb191 |
completed | April 18, 2026, 9:35 p.m. |
| PDg | Predicate description generation | batch_69e42d8eefa88190a700c7c1b4213e46 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:24 a.m.