Triple
T1614980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dean Kamen |
E34695
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | Segway PT |
E28622
|
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: Segway PT | Statement: [Dean Kamen, knownFor, Segway PT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Segway PT Context triple: [Dean Kamen, knownFor, Segway PT]
-
A.
Segway PT
chosen
The Segway PT is a self-balancing, two-wheeled personal transporter that became widely known as an innovative but niche urban mobility device.
-
B.
Segway Inc.
Segway Inc. is an American company best known for developing and producing self-balancing personal transporters and related electric mobility devices.
-
C.
iBOT mobility system
The iBOT mobility system is an advanced powered wheelchair that uses gyroscopic technology to climb stairs, elevate users to standing height, and navigate challenging terrain.
-
D.
Velo
Velo is a nicotine pouch brand owned by British American Tobacco, marketed as a smokeless alternative to traditional cigarettes.
-
E.
M-Line Trolley
M-Line Trolley is a heritage streetcar system operating in Dallas, Texas, providing free public transportation along the McKinney Avenue and Uptown 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_69a885ffc5ec819091afa325d5f9611c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9098f384c81909ef836ee779466e2 |
completed | March 5, 2026, 4:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad51ca2bc48190abb83f4d84782334 |
completed | March 8, 2026, 10:39 a.m. |
Created at: March 4, 2026, 7:28 p.m.