Triple
T21850176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Skilling |
E539483
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | WGN Radio |
—
|
NE NERFINISHED |
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: WGN Radio | Statement: [Tom Skilling, employer, WGN Radio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WGN Radio Context triple: [Tom Skilling, employer, WGN Radio]
-
A.
WGN Radio
chosen
WGN Radio is a historic Chicago-based AM radio station known for its news, talk, and sports programming and long association with the Chicago Tribune.
-
B.
WGN-TV
WGN-TV is a Chicago-based television station and former national superstation known for its local news, sports broadcasts, and syndicated programming.
-
C.
WGN
WGN is the National Rail station code for Wigan North Western railway station in Greater Manchester, England.
-
D.
WGN America
WGN America is a U.S.-based cable television network known for airing syndicated series, movies, and original programming to a national audience.
-
E.
WGNQ-CD
WGNQ-CD is a low-power Class A television station in the Chicago market that operates as a sister outlet to major ABC affiliate WLS-TV.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c476c3c88190a92d08ebb59a128a |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0bd582ca48190890648fdee2a0c6e |
completed | April 28, 2026, 1:59 p.m. |
Created at: April 16, 2026, 6:55 p.m.