Triple
T1903393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broca's aphasia |
E37743
|
entity |
| Predicate | typicalLesionLocation |
P21283
|
FINISHED |
| Object | left inferior frontal gyrus |
—
|
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: left inferior frontal gyrus | Statement: [Broca's aphasia, typicalLesionLocation, left inferior frontal gyrus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalLesionLocation Context triple: [Broca's aphasia, typicalLesionLocation, left inferior frontal gyrus]
-
A.
locatedOnBody
Indicates that one entity is physically situated on the surface or external part of another entity’s body.
-
B.
apseLocation
Indicates the specific place or position where an apse is situated within a larger structure or context.
-
C.
hasBodyRegion
chosen
Indicates that an entity possesses, includes, or is associated with a specific anatomical or bodily region.
-
D.
pathologyFeature
Indicates that one entity is a pathological characteristic, sign, or abnormal finding associated with another entity in a medical or biological context.
-
E.
typicalUseLocation
Indicates the usual or most common location where an entity is used or operates.
- 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_69a8861be7148190a680937ec451a304 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb34d94fc8190a5bf1e582c77c725 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafe9f8b0819086d8f6288511c66d |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:35 p.m.