Triple
T16690095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secretary of State for Foreign Affairs and War |
E405570
|
entity |
| Predicate | combinesFunctionOf |
P94092
|
FINISHED |
| Object | foreign affairs ministry |
—
|
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: foreign affairs ministry | Statement: [Secretary of State for Foreign Affairs and War, combinesFunctionOf, foreign affairs ministry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combinesFunctionOf Context triple: [Secretary of State for Foreign Affairs and War, combinesFunctionOf, foreign affairs ministry]
-
A.
combinedFunction
Indicates that multiple functions or operations are brought together and applied as a single, unified function or process.
-
B.
combinesFeaturesOf
chosen
Indicates that one entity integrates or merges characteristics, attributes, or functionalities originating from multiple other entities.
-
C.
knownForCombining
Indicates a relationship where one entity is recognized or notable for bringing together or merging multiple elements, entities, or aspects into a unified whole.
-
D.
combinedIn
Indicates that two or more entities are merged, joined, or used together to form a single combined whole or context.
-
E.
combiningClass
Indicates that one entity functions as a combining diacritic or mark that attaches to a base character, specifying how it combines in text rendering or encoding.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ea8cabc8190ba321503399960da |
completed | April 18, 2026, 12:52 p.m. |
| PD | Predicate disambiguation | batch_69e319bc73908190a0e38bc926b31f10 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.