Triple
T4689759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BCG vaccine |
E104005
|
entity |
| Predicate | protectsBestAgainst |
P20171
|
FINISHED |
| Object | severe forms of tuberculosis in children |
—
|
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: severe forms of tuberculosis in children | Statement: [BCG vaccine, protectsBestAgainst, severe forms of tuberculosis in children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectsBestAgainst Context triple: [BCG vaccine, protectsBestAgainst, severe forms of tuberculosis in children]
-
A.
protects
Indicates taking action to keep someone or something safe from harm, danger, or negative effects.
-
B.
providesProtectionAgainst
chosen
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
-
C.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
D.
aimsToProtect
Indicates an intention or purpose to safeguard or defend one entity, value, or condition from harm, risk, or undesirable outcomes.
-
E.
protectsRight
Indicates that one entity safeguards, upholds, or defends the legal or moral rights of another entity.
- 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_69bd43df91f481908e9add1b617b60ef |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd66059bfc8190885d26d05dd38df1 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd6219da948190bbbb50f08573ab4d |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:16 p.m.