Triple
T28654950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Directive 94/45/EC |
E725304
|
entity |
| Predicate | scopeCondition |
P165180
|
FINISHED |
| Object | at least 1000 employees in the EU or EEA |
—
|
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: at least 1000 employees in the EU or EEA | Statement: [Directive 94/45/EC, scopeCondition, at least 1000 employees in the EU or EEA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scopeCondition Context triple: [Directive 94/45/EC, scopeCondition, at least 1000 employees in the EU or EEA]
-
A.
targetedCondition
Indicates that an action, intervention, or entity is specifically directed toward affecting, treating, or addressing a particular condition.
-
B.
captureCondition
Indicates the specific circumstances or criteria under which a capture event or action is triggered or considered valid.
-
C.
subsetCondition
Indicates that one set or collection is entirely contained within another, satisfying a subset relationship condition.
-
D.
containsCondition
Indicates that one entity includes, embodies, or is associated with a particular condition.
-
E.
graphCondition
Indicates that a specified condition or set of constraints holds for a graph or graph-based structure.
- F. None of above. chosen
Provenance (4 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 28, 2026, 4:54 a.m.