Triple
T11085584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ministers’ Deputies |
E262110
|
entity |
| Predicate | hasSubStructure |
P19432
|
FINISHED |
| Object | rapporteur groups |
—
|
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: rapporteur groups | Statement: [Ministers’ Deputies, hasSubStructure, rapporteur groups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubStructure Context triple: [Ministers’ Deputies, hasSubStructure, rapporteur groups]
-
A.
containsAsSubstructure
chosen
Indicates that one structure includes another structure entirely within it as a component or embedded part.
-
B.
hasStructureAbove
Indicates that one entity has another entity positioned vertically higher or located on top of it within a structural or spatial arrangement.
-
C.
containsStructureFrom
Indicates that one entity includes or incorporates a structural component originating from another entity.
-
D.
hasSubset
Indicates that one set is entirely contained within another set, with all elements of the first set also belonging to the second.
-
E.
hasSubcomponent
Indicates that one entity is a constituent part or component of another, larger 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d799c2c7d4819087ac793153340178 |
completed | April 9, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69d744185a5881909ba4cf151d1798ec |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.