Triple
T26208575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Electric Foundation |
E655419
|
entity |
| Predicate | notableReleaseFormat |
P32198
|
FINISHED |
| Object | cassette |
—
|
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: cassette | Statement: [British Electric Foundation, notableReleaseFormat, cassette]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableReleaseFormat Context triple: [British Electric Foundation, notableReleaseFormat, cassette]
-
A.
typicalReleaseFormat
chosen
Indicates the usual or standard format in which something is released or published.
-
B.
notableFormat
Indicates that something is particularly recognized or distinguished for being in a specific format.
-
C.
notableRecordingMedium
Indicates that an entity is notably recorded, documented, or expressed using a particular medium or format.
-
D.
notableRelease
Indicates that an entity is a significant or prominent release (such as a major version, edition, or launch) associated with another entity.
-
E.
firstReleaseFormat
Indicates the original medium or format in which something (such as a work or product) was first released.
- 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69fe6fea4a288190bf8615c5d6bf41b4 |
completed | May 8, 2026, 11:21 p.m. |
| PD | Predicate disambiguation | batch_69fe6f774de08190975a2393b9a1fd22 |
completed | May 8, 2026, 11:19 p.m. |
Created at: April 26, 2026, 8:51 p.m.