Triple
T17077965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EXPN |
E414397
|
entity |
| Predicate | hasCompanyBusiness |
P21206
|
FINISHED |
| Object | Global information services |
—
|
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: Global information services | Statement: [EXPN, hasCompanyBusiness, Global information services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompanyBusiness Context triple: [EXPN, hasCompanyBusiness, Global information services]
-
A.
hasBusiness
chosen
Indicates that one entity owns, operates, or is formally associated with a business entity.
-
B.
hasBusinessIn
Indicates that one entity conducts, operates, or maintains business activities within the jurisdiction, location, or domain of another entity.
-
C.
hasBusinesses
Indicates that an entity owns, operates, or is associated with one or more businesses.
-
D.
hasParentCompanyBusiness
Indicates that one company operates as a business owned or controlled by another company that serves as its parent company.
-
E.
hasBusinessOperationsIn
Indicates that a business or organization conducts commercial or operational activities within a specified geographic location or jurisdiction.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc625c48190b679a521180e10ad |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.