Triple
T2576591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Zimmer |
E57789
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Lyft (with Logan Green) |
E7323
|
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: Lyft (with Logan Green) | Statement: [John Zimmer, founded, Lyft (with Logan Green)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyft (with Logan Green) Context triple: [John Zimmer, founded, Lyft (with Logan Green)]
-
A.
Lyft Pink
Lyft Pink is Lyft’s paid membership program that offers riders benefits like discounted fares, priority support, and other perks on the Lyft platform.
-
B.
Lyft
chosen
Lyft is a major American ride-hailing and transportation company that connects passengers with drivers through a mobile app platform.
-
C.
Travis Kalanick
Travis Kalanick is an American entrepreneur best known as the co-founder and former CEO of the ride-hailing company Uber.
-
D.
Uber Green
Uber Green is an eco-focused ride option from Uber that connects riders with drivers using low-emission or electric vehicles.
-
E.
Allison Chesky
Allison Chesky is known as the sister of Airbnb co-founder and CEO Brian Chesky.
- 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_69ab4a51410081908501dcf8bad9adc4 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd3a606e481909bcea46de468bb99 |
completed | March 7, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af6576a0a8819080d9241801675b19 |
completed | March 10, 2026, 12:27 a.m. |
Created at: March 6, 2026, 9:49 p.m.