Triple
T11649580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helios Records |
E276865
|
entity |
| Predicate | sourceCatalogue |
P69156
|
FINISHED |
| Object | Hyperion Records catalogue |
—
|
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: Hyperion Records catalogue | Statement: [Helios Records, sourceCatalogue, Hyperion Records catalogue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceCatalogue Context triple: [Helios Records, sourceCatalogue, Hyperion Records catalogue]
-
A.
sourceCategory
Indicates the classification or type from which something originates or is derived.
-
B.
source
Indicates that something originates from, is derived from, or is provided by a particular entity or location.
-
C.
catalogueFor
Indicates that one entity serves as a catalog or organized listing that describes, indexes, or inventories another entity.
-
D.
sourceStatus
Indicates the current state or condition of a given source within a process, system, or workflow.
-
E.
catalogueSystem
chosen
Indicates a relationship where one entity serves as or belongs to a cataloging system that organizes, indexes, or classifies other entities.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a2cea9308190a13f7dd995ea07a4 |
completed | April 10, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69d85ddc780481909a3bc63832fe2bd2 |
completed | April 10, 2026, 2:18 a.m. |
Created at: April 8, 2026, 9:39 p.m.