Triple
T2504144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mycobacterium tuberculosis |
E52537
|
entity |
| Predicate | biosafetyLevel |
P32294
|
FINISHED |
| Object | BSL-3 |
—
|
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: BSL-3 | Statement: [Mycobacterium tuberculosis, biosafetyLevel, BSL-3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: biosafetyLevel Context triple: [Mycobacterium tuberculosis, biosafetyLevel, BSL-3]
-
A.
isReservoirOf
Indicates that one entity serves as a storage source or container holding a particular substance, resource, or quantity for another entity or purpose.
-
B.
safetyLabel
chosen
Indicates that an entity has been assigned a safety-related classification or warning status.
-
C.
classificationLevel
Indicates the degree or tier within an ordered system or hierarchy to which something is assigned for categorization or control purposes.
-
D.
pathogenicityToHumans
Indicates that an entity has the capacity to cause disease or harmful health effects in humans.
-
E.
amenityLevel
Indicates the degree or quality of facilities, services, or conveniences provided in relation to something.
- 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_69ab4957b3a88190adf968ae0c1b931c |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd1cd2db0819087d21ec49ffd9585 |
completed | March 7, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69abd0bba5348190bb4637d3165cb339 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:46 p.m.