Triple
T22457505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ICH Rules of Procedure |
E555152
|
entity |
| Predicate | appliesInDomain |
P1248
|
FINISHED |
| Object | pharmaceutical regulatory harmonisation |
—
|
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: pharmaceutical regulatory harmonisation | Statement: [ICH Rules of Procedure, appliesInDomain, pharmaceutical regulatory harmonisation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesInDomain Context triple: [ICH Rules of Procedure, appliesInDomain, pharmaceutical regulatory harmonisation]
-
A.
appliesTo
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
-
B.
appliesFrom
Indicates that a rule, condition, or effect begins to be applicable starting from a specific point in time or state.
-
C.
appliesAt
Indicates that an action, rule, or condition is relevant to or in effect at a specific location, context, or point in time.
-
D.
usedInDomain
chosen
Indicates that something (such as a concept, method, or resource) is applied or utilized within a particular domain or field.
-
E.
appliesToFeature
Indicates that something (such as a rule, constraint, or configuration) is relevant to, or governs, a specific feature.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7d00208190955a70e2c22d25a4 |
completed | April 29, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:48 p.m.