Triple
T32591886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hazel Grace Lancaster |
E833092
|
entity |
| Predicate | usesMedicalDevice |
P183529
|
FINISHED |
| Object | oxygen tank |
—
|
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: oxygen tank | Statement: [Hazel Grace Lancaster, usesMedicalDevice, oxygen tank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesMedicalDevice Context triple: [Hazel Grace Lancaster, usesMedicalDevice, oxygen tank]
-
A.
diseaseUsed
Indicates that a particular disease is employed or utilized as a tool, model, or condition within a given context or process.
-
B.
usesMedicalKnowledge
Indicates that an entity applies or relies on medical knowledge in performing an action or making a decision.
-
C.
usesDrug
Indicates that an entity consumes, administers, or otherwise makes use of a specified drug.
-
D.
usedMedicalPersonnel
Indicates that an entity employed or made use of medical personnel in performing an action or providing a service.
-
E.
usedDesignDevice
Indicates that one entity employed or operated a particular design-related device or tool.
- F. None of above. chosen
Provenance (4 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_69f34929ff648190aded9424aa7564ae |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7a01efcc08190bba489a9099b8684 |
completed | May 3, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69f79e4888248190be2f63cdfb5cd7b7 |
completed | May 3, 2026, 7:13 p.m. |
| PDg | Predicate description generation | batch_69f79f477c4c8190a35cb6d87b1dcbd1 |
completed | May 3, 2026, 7:17 p.m. |
Created at: May 1, 2026, 1:05 a.m.