Triple
T28185657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Magogo kaDinuzulu |
E716170
|
entity |
| Predicate | recordingsMadeBy |
P122453
|
FINISHED |
| Object | Hugh Tracey |
—
|
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: Hugh Tracey | Statement: [Princess Magogo kaDinuzulu, recordingsMadeBy, Hugh Tracey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordingsMadeBy Context triple: [Princess Magogo kaDinuzulu, recordingsMadeBy, Hugh Tracey]
-
A.
recordingsFrom
Indicates a relationship where one entity serves as the source or origin of recordings that are associated with or derived from it.
-
B.
recordingOf
Indicates that one entity is an audio or video capture or performance that documents, represents, or preserves another entity (such as a work, event, or expression).
-
C.
artistRecorded
Indicates that an artist has recorded a particular musical work, track, or album.
-
D.
areRecordedBy
chosen
Indicates that an event, observation, or piece of information is captured or documented by a specific recording agent, device, or process.
-
E.
recordedFor
Indicates that something has been documented, captured, or logged on behalf of or in association with a particular entity or context.
- 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_69efd6b4fc5c81909dd88f01a8c2b35d |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f739a638748190808e7a2930dce16e |
completed | May 3, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f732f2dc6c8190a4e86da98cc5eb05 |
completed | May 3, 2026, 11:35 a.m. |
Created at: April 27, 2026, 10:22 p.m.