Triple
T26463136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OLAF |
E665687
|
entity |
| Predicate | hasTypeOfInvestigation |
P11082
|
FINISHED |
| Object | external investigations |
—
|
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: external investigations | Statement: [OLAF, hasTypeOfInvestigation, external investigations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfInvestigation Context triple: [OLAF, hasTypeOfInvestigation, external investigations]
-
A.
typeOfInvestigation
chosen
Indicates the specific kind or category of investigation being conducted or referred to in the relationship.
-
B.
containsInvestigationOf
Indicates that one entity includes or encompasses an investigation or inquiry concerning another entity.
-
C.
hasInvestigationTrigger
Indicates that one entity serves as the cause, condition, or event that initiates or justifies an investigation into another entity.
-
D.
areInvestigatedFor
Indicates that one or more entities are the subject of an investigation concerning a particular issue, incident, or alleged wrongdoing.
-
E.
hasInvestigationTarget
Indicates that an investigation is directed toward or focused on a particular target 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_69ee883e812c8190a9b5a9cdb87fee5e |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 27, 2026, 12:14 a.m.