Triple
T103361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Surgery, Duke University |
E2087
|
entity |
| Predicate | conductsResearchIn |
P934
|
FINISHED |
| Object | clinical surgery |
—
|
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: clinical surgery | Statement: [Department of Surgery, Duke University, conductsResearchIn, clinical surgery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conductsResearchIn Context triple: [Department of Surgery, Duke University, conductsResearchIn, clinical surgery]
-
A.
hasResearchArea
chosen
Indicates that an entity (such as a person, project, or organization) is associated with or focused on a particular field or area of research.
-
B.
publishedResearchOn
Indicates that an entity has authored and made publicly available scholarly or scientific work concerning a particular subject or topic.
-
C.
researchStrength
Indicates the degree to which an entity possesses strong capabilities, performance, or impact in conducting research.
-
D.
researchProgram
Indicates that an entity is engaged in, associated with, or part of a structured research initiative or program.
-
E.
researchClassification
Indicates that an entity is assigned a specific category or type within a research-related classification scheme.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a2563a6ff48190bec582fb2f99b7af |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.