Triple
T18020901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pericardium |
E431113
|
entity |
| Predicate | anatomicalRelation |
P93525
|
FINISHED |
| Object | Anterior to esophagus |
—
|
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: Anterior to esophagus | Statement: [Pericardium, anatomicalRelation, Anterior to esophagus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: anatomicalRelation Context triple: [Pericardium, anatomicalRelation, Anterior to esophagus]
-
A.
morphologicalRelation
Indicates a relationship between linguistic forms where one word or morpheme is derived from, inflected from, or otherwise morphologically related to another.
-
B.
standsInRelationTo
Indicates that one entity is connected to another by some specified relationship, without constraining the nature or direction of that relationship.
-
C.
anatomicalFeature
Indicates that one entity is an anatomical part, structure, or feature of another entity.
-
D.
anatomicalType
Indicates that one entity is classified as a specific anatomical category or kind of anatomical structure in relation to another.
-
E.
alignmentRelation
chosen
Indicates that one entity is positioned, oriented, or arranged in a specific way relative to another entity.
- 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_69e4b9c1c5f88190a059ce4f86f7ed36 |
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.