Triple
T21153704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaiser Industries |
E521257
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Kaiser Aluminum |
—
|
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: Kaiser Aluminum | Statement: [Kaiser Industries, associatedWith, Kaiser Aluminum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaiser Aluminum Context triple: [Kaiser Industries, associatedWith, Kaiser Aluminum]
-
A.
Kaiser Aluminum
chosen
Kaiser Aluminum is an American industrial company specializing in the production of fabricated aluminum products for aerospace, automotive, and other high-performance applications.
-
B.
Alcoa
Alcoa is a major American industrial corporation known primarily for its global production of aluminum and related engineered products.
-
C.
Alcoa
Alcoa is a small industrial city in Blount County, Tennessee, historically centered around aluminum production and part of the Knoxville metropolitan area.
-
D.
Mitsubishi Aluminum
Mitsubishi Aluminum is a Mitsubishi Group company specializing in the production and processing of aluminum materials and related products.
-
E.
Alcan
Alcan is a French publishing house known for issuing significant academic and sociological works in the late 19th and early 20th centuries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b50d1ea481909c07e63c3ead9316 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7252929748190afd85be40294293f |
completed | April 21, 2026, 7:20 a.m. |
Created at: April 16, 2026, 2:58 p.m.