Triple
T13894725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speex |
E334057
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | Opus |
E818774
|
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: Opus | Statement: [Speex, successor, Opus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Opus Context triple: [Speex, successor, Opus]
-
A.
Opus
Opus was the chief city of the ancient Greek region of Eastern Locris, known as Opuntian Locris.
-
B.
Opus
Opus is a 2019 studio album by American singer Marc Anthony, known for its salsa tracks and his return to original material after several years.
-
C.
Opus
chosen
Opus is a versatile, royalty-free audio codec designed for interactive speech and high-fidelity music streaming over the internet.
-
D.
Opus Paramirum
Opus Paramirum is a foundational medical treatise by Paracelsus that outlines his revolutionary theories on disease, pathology, and the principles of chemical medicine.
-
E.
Opus 200
Opus 200 is a non-fiction collection by Isaac Asimov that surveys and reflects on his extensive body of work up to his 200th published book.
- 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_69d81c5dd2d48190b7a5fc1e009de936 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de23a741908190bdf46d76c5f1411a |
completed | April 14, 2026, 11:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c71eb1808190b0a3a28a8011e9c7 |
completed | May 3, 2026, 10:07 p.m. |
Created at: April 9, 2026, 10:15 p.m.