Triple
T27670902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Converge FiberXers |
E697659
|
entity |
| Predicate | acquiredFranchiseFrom |
P93473
|
FINISHED |
| Object | Alaska Milk Corporation |
—
|
NE NERFINISHED |
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: Alaska Milk Corporation | Statement: [Converge FiberXers, acquiredFranchiseFrom, Alaska Milk Corporation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acquiredFranchiseFrom Context triple: [Converge FiberXers, acquiredFranchiseFrom, Alaska Milk Corporation]
-
A.
acquiredFranchise
chosen
Indicates that one entity has obtained ownership or control of a franchise from another entity or source.
-
B.
franchiseOf
Indicates that one entity operates as a franchise belonging to or licensed by another entity.
-
C.
acquiredFranchiseYear
Indicates the year in which an entity obtained ownership or control of a franchise.
-
D.
associatedFranchise
Indicates a relationship where one entity is linked to, or belongs within, a particular franchise or franchise universe.
-
E.
franchiseSoldTo
Indicates that the rights to operate or own a franchise have been transferred from one party to another.
- 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_69ef590d458c81909583290c3cd0478b |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 2:41 p.m.