Triple
T2134274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Skoll |
E46613
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | eBay |
E7814
|
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: eBay | Statement: [Jeff Skoll, employer, eBay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: eBay Context triple: [Jeff Skoll, employer, eBay]
-
A.
eBay
chosen
eBay is a global e-commerce company best known for its online auction and consumer-to-consumer sales platform.
-
B.
Alibaba.com
Alibaba.com is a leading global online business-to-business (B2B) marketplace that connects suppliers, primarily manufacturers and wholesalers, with buyers around the world.
-
C.
Taobao
Taobao is a major Chinese online shopping platform known for its vast marketplace of consumer-to-consumer and business-to-consumer goods.
-
D.
AliExpress
AliExpress is a global online retail marketplace that connects consumers worldwide with primarily Chinese manufacturers and sellers offering a wide range of low-cost products.
-
E.
Marketplace
Marketplace is a long-running public radio program and podcast focused on in-depth coverage and analysis of business, economic, and financial news.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbba24004819091ffb9440e8615fa |
completed | March 7, 2026, 5:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6533c7f081909860c89a2a53ad49 |
completed | March 9, 2026, 6:14 a.m. |
Created at: March 4, 2026, 7:44 p.m.