Triple
T11774360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zimride |
E279979
|
entity |
| Predicate | coFounder |
P2835
|
FINISHED |
| Object | Logan Green |
E66189
|
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: Logan Green | Statement: [Zimride, coFounder, Logan Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Logan Green Context triple: [Zimride, coFounder, Logan Green]
-
A.
Logan Green
chosen
Logan Green is an American entrepreneur best known as the co-founder and former CEO of the ride-sharing company Lyft.
-
B.
Tim Green
Tim Green is a researcher who co-authored the landmark 2021 Nature paper on AlphaFold, the deep learning system for highly accurate protein structure prediction.
-
C.
Tim Green
Tim Green is an American musician and producer best known as a guitarist in the instrumental rock band The Fucking Champs and for his work in the underground rock scene.
-
D.
Austin Hopkinson
Austin Hopkinson was a British industrialist and Conservative politician known for his work in engineering and his tenure as a Member of Parliament in the early 20th century.
-
E.
Quinn Martin
Quinn Martin was a prolific American television producer best known for creating and producing numerous hit crime and drama series during the 1960s and 1970s.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a55f415081908eec78cb2c956598 |
completed | April 10, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f166aed0908190b43e01b674382b1f |
completed | April 29, 2026, 2:02 a.m. |
Created at: April 8, 2026, 9:41 p.m.