Triple
T16501089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AM |
E400799
|
entity |
| Predicate | transmitterType |
P123793
|
FINISHED |
| Object | AM broadcast transmitter |
—
|
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: AM broadcast transmitter | Statement: [AM, transmitterType, AM broadcast transmitter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transmitterType Context triple: [AM, transmitterType, AM broadcast transmitter]
-
A.
transponderType
Indicates the specific kind or category of transponder associated with an entity or used in a given context.
-
B.
transmissionPowerType
Indicates the type or category of power used to transmit a signal or data between entities.
-
C.
transmissionType
Indicates the method or medium through which something is transmitted or conveyed from one entity to another.
-
D.
transmitterLocation
Indicates the spatial position or place where a transmitter is situated or operates.
-
E.
hasFMTransmitter
Indicates that one entity is equipped with or includes an FM radio transmitter component or capability.
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e4ddc88819081fedb726add3e96 |
completed | April 18, 2026, 7:10 a.m. |
| PD | Predicate disambiguation | batch_69e296902d6c8190884ddb612b8c5b36 |
completed | April 17, 2026, 8:22 p.m. |
| PDg | Predicate description generation | batch_69e2d7f97e548190a474691a152bd8e8 |
completed | April 18, 2026, 1:01 a.m. |
Created at: April 10, 2026, 5:14 a.m.