Triple
T4130170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | H. J. Heinz family members |
E85020
|
entity |
| Predicate | hasBusinessLegacy |
P51922
|
FINISHED |
| Object | global ketchup production |
—
|
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 ketchup production | Statement: [H. J. Heinz family members, hasBusinessLegacy, global ketchup production]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBusinessLegacy Context triple: [H. J. Heinz family members, hasBusinessLegacy, global ketchup production]
-
A.
hasLegacy
Indicates that an entity leaves behind a lasting impact, influence, or inheritance that continues to exist or be recognized over time.
-
B.
hasLegacyInstitution
Indicates that an entity is historically derived from, or continues the role or traditions of, an earlier institution.
-
C.
businessLegacy
chosen
Indicates that one entity inherits, continues, or is significantly shaped by the business practices, reputation, or assets established by another entity.
-
D.
hasBusiness
Indicates that one entity owns, operates, or is formally associated with a business entity.
-
E.
hasPartInLegacy
Indicates that an entity includes another entity as a component or constituent specifically within its legacy or historically inherited structure.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af03a0f3408190adba7a8513bd3d12 |
completed | March 9, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69af01883b6c8190a482ead589a131a5 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:42 p.m.