Triple
T38164436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Advanced Trauma Life Support |
E953104
|
entity |
| Predicate | certificationValidity |
P33304
|
FINISHED |
| Object | 4 years |
—
|
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: 4 years | Statement: [Advanced Trauma Life Support, certificationValidity, 4 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: certificationValidity Context triple: [Advanced Trauma Life Support, certificationValidity, 4 years]
-
A.
certificationDate
Indicates the date on which an entity was officially certified or granted a formal certification.
-
B.
validityPeriodEnd
Indicates the date and time at which a previously valid state, authorization, or condition ceases to be valid.
-
C.
hasValidityPeriod
chosen
Indicates that something is associated with a specific time span during which it is considered valid or in effect.
-
D.
certificationBy
Indicates that one entity formally attests to, approves, or validates the qualifications, standards, or authenticity of another entity.
-
E.
licenseExpirationYear
Indicates the calendar year in which a given license ceases to be valid or legally effective.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.