Triple
T3268138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Friedman |
E68576
|
entity |
| Predicate | coFounded |
P104
|
FINISHED |
| Object | Fitbit |
E4030
|
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: Fitbit | Statement: [Eric Friedman, coFounded, Fitbit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fitbit Context triple: [Eric Friedman, coFounded, Fitbit]
-
A.
Fitbit
chosen
Fitbit is a consumer electronics and fitness company best known for its wearable activity trackers and smartwatches that monitor health and exercise metrics.
-
B.
Fitbit Premium
Fitbit Premium is a paid membership service that enhances Fitbit devices and apps with advanced health insights, personalized coaching, and additional wellness features.
-
C.
Fitbit Sense
Fitbit Sense is a health-focused smartwatch by Fitbit that offers advanced fitness tracking, heart and stress monitoring, and smart features like notifications and apps.
-
D.
Fitbit Ionic
The Fitbit Ionic is a GPS-enabled fitness-focused smartwatch that tracks activity, heart rate, sleep, and supports apps and notifications.
-
E.
Fitbit Inspire series
The Fitbit Inspire series is a line of slim, entry-level fitness trackers designed to monitor daily activity, sleep, and basic health metrics with long battery life and smartphone connectivity.
- 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_69ad8590444081909e8107a8aeef3a23 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adafcf9c6c819092f9c618b778b46d |
completed | March 8, 2026, 5:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e83e11f081909d64287c0902124a |
completed | March 12, 2026, 4:22 p.m. |
Created at: March 8, 2026, 3:09 p.m.