Triple
T14971346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew Berger |
E373325
|
entity |
| Predicate | seeksTreatmentFor |
P95317
|
FINISHED |
| Object | dry eye |
—
|
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: dry eye | Statement: [Matthew Berger, seeksTreatmentFor, dry eye]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seeksTreatmentFor Context triple: [Matthew Berger, seeksTreatmentFor, dry eye]
-
A.
usesTreatment
Indicates that one entity applies or employs a particular treatment or therapeutic method on or for another entity.
-
B.
hasReceivedTreatmentFor
chosen
Indicates that an entity has undergone or been given a treatment in relation to a specified condition, issue, or problem.
-
C.
remedySought
Indicates that a particular legal or corrective action is being requested as a solution or relief in response to a problem or dispute.
-
D.
knownForTreatmentOf
Indicates that an entity is recognized or notable for providing treatment or medical care for a particular condition, disease, or type of patient.
-
E.
treats
Indicates that one entity provides medical care or therapeutic intervention 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6e59a7c8190a1634a706ea68fda |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:50 a.m.