Triple
T4132135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | rVSV-ZEBOV |
E85063
|
entity |
| Predicate | trialDesign |
P54033
|
FINISHED |
| Object | cluster-randomized ring vaccination trial |
—
|
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: cluster-randomized ring vaccination trial | Statement: [rVSV-ZEBOV, trialDesign, cluster-randomized ring vaccination trial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trialDesign Context triple: [rVSV-ZEBOV, trialDesign, cluster-randomized ring vaccination trial]
-
A.
trialName
Indicates the designated name or title assigned to a specific trial.
-
B.
coordinatesClinicalTrialsFor
Indicates that one entity organizes, manages, or oversees the planning and execution of clinical trials on behalf of another entity.
-
C.
trialAfter
Indicates that one trial or legal proceeding occurs subsequent to another in time or sequence.
-
D.
experimentedOn
Indicates that one entity conducted experiments or tests on another entity as the subject of investigation.
-
E.
trialMode
Indicates that an entity is operating in a temporary, limited-capability trial state rather than in full or permanent mode.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af03a0f3408190adba7a8513bd3d12 |
completed | March 9, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69af01883b6c8190a482ead589a131a5 |
completed | March 9, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69af039fb19c8190b20e62a3b3ad25c1 |
completed | March 9, 2026, 5:30 p.m. |
Created at: March 9, 2026, 3:42 p.m.