Triple
T102677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kraft Group |
E2073
|
entity |
| Predicate | hasBusinessDivision |
P7588
|
FINISHED |
| Object | paper and packaging |
—
|
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: paper and packaging | Statement: [Kraft Group, hasBusinessDivision, paper and packaging]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBusinessDivision Context triple: [Kraft Group, hasBusinessDivision, paper and packaging]
-
A.
hasDivisionLevel
Indicates that one entity is associated with a specific hierarchical or organizational division level of another entity.
-
B.
hasBusinessDistrict
Indicates that a place or administrative area contains or includes a designated business district within its boundaries.
-
C.
hasHeadquartersType
Indicates the specific kind or classification of headquarters associated with an entity.
-
D.
hasEconomicOrganization
Indicates that an entity possesses, is associated with, or participates in a specific economic organization or institutional economic structure.
-
E.
hasSubdivision
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a2563a6ff48190bec582fb2f99b7af |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a258de46888190835db2b21a093eaa |
completed | Feb. 28, 2026, 2:54 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.