Triple
T5155876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flat Holm |
E116306
|
entity |
| Predicate | radioExperimentType |
P62271
|
FINISHED |
| Object | wireless telegraphy |
—
|
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: wireless telegraphy | Statement: [Flat Holm, radioExperimentType, wireless telegraphy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: radioExperimentType Context triple: [Flat Holm, radioExperimentType, wireless telegraphy]
-
A.
radioFormat
Indicates the specific type or style of radio programming or broadcast format associated with an entity.
-
B.
radioAnnouncers
Indicates that one entity serves as a radio announcer for, or in association with, another entity.
-
C.
radioInterface
Indicates a relationship where one entity provides or defines the radio communication interface used by another entity for wireless connectivity or control.
-
D.
radioAdaptationDirector
Indicates that the subject served as the director of a radio adaptation of the object work or production.
-
E.
hostsExperiment
Indicates that one entity provides the environment or infrastructure in which another entity’s experiment is conducted or run.
- F. None of above. chosen
Provenance (4 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_69bd445d94788190b72e2cc563120995 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79c1354c81908176703b4853c1a4 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b0fbb88190851e2d7ae1bdcc09 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd79bf9b088190a556dc02f10204e4 |
completed | March 20, 2026, 4:45 p.m. |
Created at: March 20, 2026, 1:44 p.m.