Triple
T25346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General Motors |
E506
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Buick |
E506
|
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: Buick | Statement: [General Motors, brand, Buick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buick Context triple: [General Motors, brand, Buick]
-
A.
Chevrolet
Chevrolet is a major American automobile marque known for producing a wide range of affordable cars, trucks, and SUVs.
-
B.
General Motors
chosen
General Motors is a major American multinational automotive manufacturer known for brands such as Chevrolet, GMC, Cadillac, and Buick.
-
C.
Packard
Packard is a surname most prominently associated with David Packard, the American electrical engineer and co-founder of Hewlett-Packard.
-
D.
Oldsmobile Delmont 88
The Oldsmobile Delmont 88 is a full-size American car produced by Oldsmobile in the late 1960s, known historically for being the model involved in the Chappaquiddick incident.
-
E.
Hummer
Hummer is a line of large, military-inspired sport utility vehicles known for their rugged off-road capability, boxy design, and high fuel consumption.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a2481f9eac819093d9a950eb1ab109 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2623969188190814f662922953e39 |
completed | Feb. 28, 2026, 3:34 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.