Triple
T25772658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Electricity Building |
E649063
|
entity |
| Predicate | featuredCompany |
P132746
|
FINISHED |
| Object | Westinghouse Electric Company |
—
|
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: Westinghouse Electric Company | Statement: [Electricity Building, featuredCompany, Westinghouse Electric Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredCompany Context triple: [Electricity Building, featuredCompany, Westinghouse Electric Company]
-
A.
featuresCompany
chosen
Indicates that one entity prominently presents, highlights, or showcases a company, typically as part of content, listings, or promotional material.
-
B.
company
Indicates that an entity is a business organization engaged in commercial, industrial, or professional activities.
-
C.
targetCompanies
Indicates that certain companies are the intended focus or recipients of a particular action, effort, or objective.
-
D.
selectedCompany
Indicates that a particular company has been chosen or designated from a set of possible companies.
-
E.
homeCompany
Indicates that one entity serves as the primary or base company associated with another entity, such as a person or subsidiary.
- 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_69e7ab333b508190b6d708d8d9a328ed |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: April 22, 2026, 5:31 a.m.