Triple
T38540857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Post family |
E924830
|
entity |
| Predicate | originatedFromBusiness |
P19812
|
FINISHED |
| Object | Postum Cereal Company |
E350809
|
NE 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: Postum Cereal Company | Statement: [Post family, originatedFromBusiness, Postum Cereal Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originatedFromBusiness Context triple: [Post family, originatedFromBusiness, Postum Cereal Company]
-
A.
businessOrigin
chosen
Indicates the place, source, or context from which a business or commercial entity originates or was established.
-
B.
originatesFromWork
Indicates that something has its source, derivation, or creation in a particular work (such as a document, artwork, or publication).
-
C.
originalBusinessType
Indicates the initial or primary category of business activity or industry classification associated with an entity before any subsequent changes or reclassifications.
-
D.
hasBusiness
Indicates that one entity owns, operates, or is formally associated with a business entity.
-
E.
originallyFromWorkType
Indicates that one entity was derived, adapted, or sourced from an original work of a specified type (e.g., book, film, artwork).
- F. None of above.
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_69f76eadeac081909cdfdd0474cb6765 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41e030e33481908e48fba32b0fe492 |
completed | June 29, 2026, 3:02 a.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.