Triple
T7125631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arrow Film & Video |
E166051
|
entity |
| Predicate | mediaFormatEra |
P22765
|
FINISHED |
| Object | VHS era |
—
|
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: VHS era | Statement: [Arrow Film & Video, mediaFormatEra, VHS era]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediaFormatEra Context triple: [Arrow Film & Video, mediaFormatEra, VHS era]
-
A.
filmEra
Indicates the historical or stylistic period in which a film was produced or to which its cinematic style belongs.
-
B.
recordingEra
chosen
Indicates the historical time period or era during which the recording was made.
-
C.
notablePlatformEra
Indicates that an entity is notably associated with a particular platform during a specific era or period of prominence.
-
D.
targetAudienceEra
Indicates the historical period or era for which something (such as a work, product, or message) is primarily intended or designed as its audience.
-
E.
distributorEra
Indicates a temporal relationship specifying the era or time period during which a distributor was active or responsible for distributing something.
- 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_69c6888350588190870cd552b427a1cd |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e64d99888190a93c1822e19b5457 |
completed | March 27, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69c6e1c7289881909f3b533c384f9ed4 |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:44 p.m.