Triple
T7729173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wernicke area |
E175206
|
entity |
| Predicate | typicallyIn |
P12230
|
FINISHED |
| Object | left hemisphere |
—
|
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 hemisphere | Statement: [Wernicke area, typicallyIn, left hemisphere]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyIn Context triple: [Wernicke area, typicallyIn, left hemisphere]
-
A.
typicalIn
chosen
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
B.
typicalGoing
Indicates that an entity is engaged in or undergoing a normal, expected instance of going or movement from one place to another.
-
C.
typicallySpared
Indicates that an entity is usually not affected by, excluded from, or left untouched by a particular action, process, or condition.
-
D.
notTypically
Indicates that the referenced situation, behavior, or relationship does not usually or normally occur under standard or expected conditions.
-
E.
typicalCircumstance
Indicates the usual or commonly occurring situation, condition, or context in which an event, action, or relationship typically takes place.
- 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_69c6995e912c81909a49a2657103f786 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:06 p.m.