Triple
T1481991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Travis Kalanick |
E30977
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Red Swoosh |
E169383
|
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: Red Swoosh | Statement: [Travis Kalanick, employer, Red Swoosh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Red Swoosh Context triple: [Travis Kalanick, employer, Red Swoosh]
-
A.
Red Swoosh
chosen
Red Swoosh was a peer-to-peer content delivery and file-sharing startup later acquired by Akamai Technologies.
-
B.
Swoosh
Swoosh is the iconic curved checkmark symbol that serves as the primary brand logo of Nike, representing speed, motion, and athletic performance.
-
C.
RAF roundel
The RAF roundel is the distinctive circular insignia featuring concentric colored rings used to identify aircraft and equipment of the United Kingdom’s Royal Air Force.
-
D.
Swiss roundel
The Swiss roundel is the distinctive national insignia featuring a white cross on a red circular background used to mark Swiss military aircraft and other official equipment.
-
E.
RCAF roundel
The RCAF roundel is the distinctive circular insignia featuring a red maple leaf used to mark and identify Royal Canadian Air Force aircraft.
- 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_69a498fe55a88190ab7f9e40ace88e49 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c6782f088190930d25a56161e2b3 |
completed | March 1, 2026, 11:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad1ca4c4e481909ea0ca76841454b1 |
completed | March 8, 2026, 6:52 a.m. |
Created at: March 1, 2026, 8:11 p.m.