Triple
T19223677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Moritz |
E480681
|
entity |
| Predicate | investedIn |
P17330
|
FINISHED |
| Object | Zappos |
—
|
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: Zappos | Statement: [Michael Moritz, investedIn, Zappos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zappos Context triple: [Michael Moritz, investedIn, Zappos]
-
A.
Zappos
chosen
Zappos is a major U.S.-based online retailer best known for its extensive selection of shoes and its customer-centric service culture.
-
B.
Jet.com
Jet.com was an American e-commerce company known for its dynamic pricing model and rapid growth as a Walmart-acquired online retail platform.
-
C.
Overstock.com
Overstock.com is an American online retailer known for selling discounted furniture, home goods, and other merchandise through its e-commerce platform.
-
D.
Ross Dress for Less
Ross Dress for Less is an American off-price retail chain offering discounted brand-name clothing, footwear, home décor, and accessories.
-
E.
Karl's Shoe Stores
Karl's Shoe Stores was a prominent American retail shoe chain founded and owned by businessman Harry Karl.
- 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa95743481909314fd14e2c3d189 |
completed | April 20, 2026, 10:06 a.m. |
Created at: April 10, 2026, 1:24 p.m.