Triple
T18794583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epic Games |
E459598
|
entity |
| Predicate | owns |
P347
|
FINISHED |
| Object | Harmonix |
—
|
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: Harmonix | Statement: [Epic Games, owns, Harmonix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harmonix Context triple: [Epic Games, owns, Harmonix]
-
A.
Harmonix
chosen
Harmonix is an American video game developer best known for pioneering music and rhythm games such as the original Guitar Hero and Rock Band series.
-
B.
Korg
Korg is a rock-like Kronan warrior from the Marvel universe, best known as a humorous ally of Thor who appears in the Marvel Cinematic Universe films.
-
C.
Edirol
Edirol is a Roland Corporation brand known for its digital audio and video equipment, including interfaces, mixers, and recording devices aimed at musicians and multimedia creators.
-
D.
Mackie Academy
Mackie Academy is a secondary school serving the town of Stonehaven and the surrounding area in Aberdeenshire, Scotland.
-
E.
DAW
DAW was a United Nations division focused on promoting gender equality and advancing the status and rights of women worldwide.
- 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a01dbb308190bbbbd5a18e26451e |
completed | April 20, 2026, 3:40 a.m. |
Created at: April 10, 2026, 11:53 a.m.