Triple
T5102301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocket eBook |
E115008
|
entity |
| Predicate | developedBy |
P73
|
FINISHED |
| Object | NuvoMedia |
E115007
|
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: NuvoMedia | Statement: [Rocket eBook, developedBy, NuvoMedia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NuvoMedia Context triple: [Rocket eBook, developedBy, NuvoMedia]
-
A.
NuvoMedia
chosen
NuvoMedia was an early e-book technology company best known for creating the Rocket eBook, one of the first dedicated electronic book readers.
-
B.
Silicon Image
Silicon Image was a semiconductor company best known for pioneering digital interface technologies, including key contributions to the development and commercialization of HDMI.
-
C.
Ingenious Media
Ingenious Media is a British media investment and production company known for financing and supporting major film projects, including the acclaimed adaptation of "Life of Pi."
-
D.
Torch Media Inc.
Torch Media Inc. is a software company best known for developing the Torch web browser, which integrates media downloading and sharing features.
-
E.
Nettwerk
Nettwerk is a Canadian independent record label and management company known for working with a diverse roster of alternative, electronic, and world music artists.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7586a4a08190866aea6be625837c |
completed | March 20, 2026, 4:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bec36d231481908da4d2df53bd6507 |
completed | March 21, 2026, 4:12 p.m. |
Created at: March 20, 2026, 1:41 p.m.