Triple
T5278019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject |
E119419
|
entity | |
| Predicate | notableCompetitor |
P11706
|
FINISHED |
| Object | Etsy |
E452779
|
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: Etsy | Statement: [Pinterest, notableCompetitor, Etsy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Etsy Context triple: [Pinterest, notableCompetitor, Etsy]
-
A.
Etsy
chosen
Etsy is an online marketplace specializing in handmade, vintage, and unique factory-manufactured items, connecting independent sellers with buyers worldwide.
-
B.
eBay
eBay is a global e-commerce company best known for its online auction and consumer-to-consumer sales platform.
-
C.
Marketplace
Marketplace is a long-running public radio program and podcast focused on in-depth coverage and analysis of business, economic, and financial news.
-
D.
The Marketplace
The Marketplace is a central commercial area where vendors and shoppers gather for buying and selling goods and services.
-
E.
Trading Post
A trading post is a commercial establishment where goods are exchanged, historically serving as an early hub for trade and settlement in frontier or developing areas.
- 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_69bd446d05a8819092ad333a3f9c8d5c |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd8474e7fc8190ab5dd84f665ae6a4 |
completed | March 20, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf06d9aab08190ad9905925a849922 |
completed | March 21, 2026, 9 p.m. |
Created at: March 20, 2026, 1:51 p.m.