Triple
T18021100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pulmonary artery |
E431117
|
entity |
| Predicate | relatedCondition |
P28410
|
FINISHED |
| Object | pulmonary embolism |
—
|
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: pulmonary embolism | Statement: [Pulmonary artery, relatedCondition, pulmonary embolism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedCondition Context triple: [Pulmonary artery, relatedCondition, pulmonary embolism]
-
A.
conditionRelatesTo
Indicates that one condition is relevant, connected, or applicable to another condition or contextual factor.
-
B.
associatedWithCondition
chosen
Indicates that an entity has a relevant connection or linkage to a particular condition (such as a disease, state, or circumstance), without specifying the nature or strength of that connection.
-
C.
relatedRule
Indicates that one rule is connected or associated with another rule, typically through some logical, structural, or referential relationship.
-
D.
containsCondition
Indicates that one entity includes, embodies, or is associated with a particular condition.
-
E.
equalityCondition
Indicates that two values, expressions, or attributes must be exactly the same for the condition to be satisfied.
- 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_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. |
Created at: April 10, 2026, 10:24 a.m.