Triple
T35682929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benjamin Buford "Bubba" Blue |
E1031060
|
entity |
| Predicate | plansBusinessWith |
P166859
|
FINISHED |
| Object | Forrest Gump |
—
|
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: Forrest Gump | Statement: [Benjamin Buford "Bubba" Blue, plansBusinessWith, Forrest Gump]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plansBusinessWith Context triple: [Benjamin Buford "Bubba" Blue, plansBusinessWith, Forrest Gump]
-
A.
plansMeetingWith
Indicates that one entity arranges or intends to organize a meeting involving another entity.
-
B.
businessPlanWith
chosen
Indicates that two or more entities are jointly associated with, responsible for, or involved in the same business plan.
-
C.
businessCombinationWith
Indicates that two or more business entities are joined through a merger, acquisition, or similar transaction to form a combined reporting or operating unit.
-
D.
businessConnection
Indicates a professional or commercial relationship exists between the entities, such as partnership, collaboration, or other business-related association.
-
E.
businessActivities
Indicates the commercial operations, transactions, or services that an entity conducts as part of its business.
- 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_69f76e0bb6608190ad3a1880be54a17d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79febaf388190994d3c643ca0da99 |
completed | May 3, 2026, 7:20 p.m. |
| PD | Predicate disambiguation | batch_69f79e4d885881908a3612e2e75cf84f |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:05 p.m.