Triple
T1349386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Management Directorate |
E28845
|
entity |
| Predicate | typeOfFunction |
P4224
|
FINISHED |
| Object | administrative support |
—
|
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: administrative support | Statement: [Management Directorate, typeOfFunction, administrative support]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFunction Context triple: [Management Directorate, typeOfFunction, administrative support]
-
A.
typeOf
chosen
Indicates that one entity is a specific kind, class, or category instance of another more general entity.
-
B.
isFunctionOf
Indicates that one quantity or property depends on and varies according to another quantity or property.
-
C.
typeOfCommand
Indicates that one entity is a specific kind or category of command in relation to another entity.
-
D.
codeType
Indicates the classification or category assigned to a particular code within a coding or encoding system.
-
E.
typeOfOperation
Indicates the specific kind or category of operation being performed or referenced in a given context.
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c268745481908be649526c18e558 |
completed | March 1, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69a4bef5857c81909ae984feb85a26ca |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:56 p.m.