Triple
T4131989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meliandou |
E85060
|
entity |
| Predicate | hasHealthEvent |
P22468
|
FINISHED |
| Object | early cluster of Ebola virus disease cases in 2013–2014 |
—
|
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: early cluster of Ebola virus disease cases in 2013–2014 | Statement: [Meliandou, hasHealthEvent, early cluster of Ebola virus disease cases in 2013–2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHealthEvent Context triple: [Meliandou, hasHealthEvent, early cluster of Ebola virus disease cases in 2013–2014]
-
A.
hasHealthConcern
Indicates that an entity has a specific health-related issue, condition, or concern associated with it.
-
B.
hadEvent
chosen
Indicates that an entity experienced, hosted, or was associated with a specific event at some point in time.
-
C.
healthIndicator
Indicates a measure or signal that reflects the health status or condition of an entity.
-
D.
hasHistoryOf
Indicates that an entity has a documented prior occurrence or background of a specified condition, event, or state.
-
E.
hasPatient
Indicates that an action, event, or process involves a specific entity as the one undergoing or receiving its effects (the patient).
- 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_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. |
Created at: March 9, 2026, 3:42 p.m.