Triple
T14955547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WBAI |
E372914
|
entity |
| Predicate | sisterStations |
P15137
|
FINISHED |
| Object | KPFT |
E1128100
|
NE 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: KPFT | Statement: [WBAI, sisterStations, KPFT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KPFT Context triple: [WBAI, sisterStations, KPFT]
-
A.
KPFT
chosen
KPFT is a listener-supported, community radio station in Houston, Texas, known for its progressive programming and affiliation with the Pacifica Radio network.
-
B.
KDKA-FM
KDKA-FM is a Pittsburgh-based commercial radio station known for its sports talk programming and affiliation with major local sports teams.
-
C.
KFPR
KFPR is the ICAO airport code for Treasure Coast International Airport, a public airport serving Fort Pierce, Florida.
-
D.
KDKA-TV
KDKA-TV is a Pittsburgh-based television station and major CBS affiliate known as one of the pioneering commercial TV outlets in the United States.
-
E.
KPFA
KPFA is a pioneering listener-supported, non-commercial radio station based in Berkeley, California, known for its progressive news, public affairs, and cultural programming.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cc73848190ac181782b20dc838 |
completed | April 15, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe968f25e08190bfbf7a3541f79add |
completed | May 9, 2026, 2:06 a.m. |
Created at: April 10, 2026, 2:40 a.m.