Triple
T33202038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mukkabla |
E849925
|
entity |
| Predicate | musicRightsHolder |
P72615
|
FINISHED |
| Object | Pyramid (original Tamil rights) |
—
|
LITERAL 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: Pyramid (original Tamil rights) | Statement: [Mukkabla, musicRightsHolder, Pyramid (original Tamil rights)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: musicRightsHolder Context triple: [Mukkabla, musicRightsHolder, Pyramid (original Tamil rights)]
-
A.
commercialRightsHolderOf
chosen
Indicates that one entity holds the legal commercial rights to exploit, license, or profit from another entity.
-
B.
musicPublishingArm
Indicates that one entity serves as the music publishing division or subsidiary of another entity, handling rights and administration of musical works on its behalf.
-
C.
musicPublisherCountry
Indicates the country in which a music publisher is based or operates.
-
D.
laterRightsHolderOfWork
Indicates that the subject is a subsequent rights holder who acquired the rights to the work after an earlier rights holder.
-
E.
rightsHolderFromYear
Indicates the year from which an entity holds legal rights (such as ownership, copyright, or usage rights) over another entity.
- F. None of above.
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_69f3495efedc8190843a5728089544b9 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd5d48855c8190bd93070b6a00d8b5 |
completed | May 8, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69fd5c9aabb88190912800d90184a89d |
completed | May 8, 2026, 3:46 a.m. |
Created at: May 1, 2026, 1:30 a.m.