Triple
T36497181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank DeTorri |
E899221
|
entity |
| Predicate | contractsDiseaseFrom |
P117232
|
FINISHED |
| Object | eating contaminated egg |
—
|
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: eating contaminated egg | Statement: [Frank DeTorri, contractsDiseaseFrom, eating contaminated egg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contractsDiseaseFrom Context triple: [Frank DeTorri, contractsDiseaseFrom, eating contaminated egg]
-
A.
contractsDisease
chosen
Indicates that an entity acquires or becomes infected with a particular disease.
-
B.
diseaseContext
Indicates that the relationship or action occurs within, is influenced by, or is specifically relevant to a particular disease or pathological condition.
-
C.
modelForDisease
Indicates that one entity serves as an experimental or representative model used to study, simulate, or understand a particular disease in another entity.
-
D.
addressesDiseaseType
Indicates that something (such as a treatment, intervention, or action) is directed toward managing, treating, or affecting a specific type of disease.
-
E.
diseaseType
Indicates that one entity is classified as a specific type or category of disease in relation 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_69f76e5b92088190933afda3f7531dd4 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff1d85441c8190931e758685a269f7 |
completed | May 9, 2026, 11:41 a.m. |
| PD | Predicate disambiguation | batch_69ff1d186cc48190b315c61e23de6551 |
completed | May 9, 2026, 11:40 a.m. |
Created at: May 3, 2026, 4:10 p.m.