Triple
T16981608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les Kelley |
E411958
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Kelley Blue Book |
E86703
|
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: Kelley Blue Book | Statement: [Les Kelley, notableWork, Kelley Blue Book]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelley Blue Book Context triple: [Les Kelley, notableWork, Kelley Blue Book]
-
A.
Kelley Blue Book
chosen
Kelley Blue Book is a widely used automotive valuation and research company known for providing trusted pricing information and reviews for new and used vehicles.
-
B.
Edmunds
Edmunds is a variant spelling of the name Edmonds, commonly used as a surname.
-
C.
Cars.com
Cars.com is a major online automotive marketplace that connects car buyers with sellers through listings, reviews, and research tools.
-
D.
Copart
Copart is a global online vehicle auction company specializing in the resale and remarketing of salvage and clean title cars, trucks, and other vehicles to buyers such as dealers, dismantlers, and the general public.
-
E.
Autotrader
Autotrader is a major online automotive marketplace where consumers can buy, sell, and research new and used vehicles.
- 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d18830ac8190a20c89a87379ae94 |
completed | April 18, 2026, 6:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d479610c8190a6281e6d4959b820 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:32 a.m.