Triple
T25729263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Diamond, Private Detective |
E645193
|
entity |
| Predicate | firstAiredOnMedium |
P17193
|
FINISHED |
| Object | radio |
—
|
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: radio | Statement: [Richard Diamond, Private Detective, firstAiredOnMedium, radio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAiredOnMedium Context triple: [Richard Diamond, Private Detective, firstAiredOnMedium, radio]
-
A.
firstAppearanceMedium
chosen
Indicates the medium (such as book, film, or game) in which an entity first appeared.
-
B.
firstAiredDuring
Indicates that one event or media item originally premiered or was first broadcast within the time period defined by another entity.
-
C.
firstAiredOnProgram
Indicates that an episode, show, or content item had its very first broadcast or premiere on a specified program.
-
D.
firstAiredWith
Indicates that one entity was initially broadcast or released at the same time as another entity.
-
E.
firstAired
Indicates the date on which something (such as a show, episode, or broadcast content) was first aired or publicly transmitted.
- 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_69e77e85254081908d79ee4e8715f283 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
Created at: April 21, 2026, 11:10 p.m.