Triple
T2651271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irving family |
E53902
|
entity |
| Predicate | corporateSeparation |
P41065
|
FINISHED |
| Object | division of major assets among K. C. Irving’s sons |
—
|
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: division of major assets among K. C. Irving’s sons | Statement: [Irving family, corporateSeparation, division of major assets among K. C. Irving’s sons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: corporateSeparation Context triple: [Irving family, corporateSeparation, division of major assets among K. C. Irving’s sons]
-
A.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
B.
separationMethod
Indicates the technique or process used to separate one substance, component, or entity from another.
-
C.
dissolvedByMerger
Indicates that an entity ceased to exist as an independent entity because it was legally combined into another entity through a merger.
-
D.
separationYear
Indicates the year in which two entities ended or dissolved their relationship or association.
-
E.
corporateStructure
Indicates how entities are organized, controlled, and related within a corporate hierarchy or ownership 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_69ab495e192081909c77b622e8e7e15a |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd93071248190820197936e3167f7 |
completed | March 7, 2026, 7:52 a.m. |
| PD | Predicate disambiguation | batch_69abd814298c8190952f05aed43f6bb8 |
completed | March 7, 2026, 7:47 a.m. |
| PDg | Predicate description generation | batch_69abd879bb808190bd2c34de1664c816 |
completed | March 7, 2026, 7:49 a.m. |
Created at: March 6, 2026, 9:53 p.m.