Triple
T24050749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabena |
E595650
|
entity |
| Predicate | formerShareholder |
P25383
|
FINISHED |
| Object | Belgian government |
—
|
NE NERFINISHED |
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: Belgian government | Statement: [Sabena, formerShareholder, Belgian government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerShareholder Context triple: [Sabena, formerShareholder, Belgian government]
-
A.
majorShareholderOf
Indicates that one entity owns a controlling or significantly large portion of another entity’s shares or equity.
-
B.
formerPartOwnerOf
chosen
Indicates that an entity previously held, but no longer holds, a partial ownership stake in another entity.
-
C.
isShareholderOf
Indicates that one entity owns shares or equity in another entity, giving it a financial stake and certain associated rights in that entity.
-
D.
formerPartner
Indicates that one entity was previously in a romantic or partnership relationship with another entity, but that relationship has since ended.
-
E.
hasShareholdersFrom
Indicates that an entity has shareholders who originate from or are associated with a specified country, region, or organization.
- 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_69e288c184b081909f1f1751fb8e299a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d9d1527c8190a4cd30bb1988a263 |
completed | April 29, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:20 p.m.