Triple
T20436599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Garage |
E501264
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Offramp |
—
|
NE NERFINISHED |
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: Offramp | Statement: [American Garage, followedBy, Offramp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Offramp Context triple: [American Garage, followedBy, Offramp]
-
A.
Offramp
chosen
Offramp is a 1982 jazz fusion album by the Pat Metheny Group, acclaimed for its atmospheric soundscapes and the popular track "Are You Going With Me?".
-
B.
UpRamp
UpRamp is an innovation and startup engagement platform that connects emerging technology companies with the global cable and broadband industry.
-
C.
Groupon
Groupon is an American e-commerce marketplace that connects subscribers with local merchants by offering discounted deals on activities, goods, and services.
-
D.
OnCourse Learning
OnCourse Learning is a professional education and training provider offering online courses and compliance solutions across industries such as financial services, real estate, and healthcare.
-
E.
Adevinta
Adevinta is a global online classifieds company that operates digital marketplaces for buying and selling goods, services, and real estate across multiple countries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4ab3cfc8190ac9bf32e932316b1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e685ef5fc8819089e3f97a63a52f86 |
completed | April 20, 2026, 8 p.m. |
Created at: April 16, 2026, 11:31 a.m.