Triple
T13787524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WJBK |
E331301
|
entity |
| Predicate | hasSisterStation |
P15137
|
FINISHED |
| Object | WXYZ-TV |
E274682
|
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: WXYZ-TV | Statement: [WJBK, hasSisterStation, WXYZ-TV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WXYZ-TV Context triple: [WJBK, hasSisterStation, WXYZ-TV]
-
A.
WSAW-TV
WSAW-TV is a local television station serving the Wausau, Wisconsin area, providing news, weather, and entertainment programming to regional viewers.
-
B.
WXYZ-TV studios
chosen
WXYZ-TV studios is the primary broadcast and production facility of Detroit’s ABC-affiliated television station WXYZ-TV, located in Southfield, Michigan.
-
C.
WPTZ
WPTZ is an NBC-affiliated television station serving the Burlington, Vermont–Plattsburgh, New York market.
-
D.
WJM-TV
WJM-TV is the fictional Minneapolis television station where the characters of The Mary Tyler Moore Show, including news writer Murray Slaughter, work.
-
E.
WSNS-TV
WSNS-TV is a Spanish-language television station in Chicago affiliated with Telemundo and owned by NBCUniversal.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0249e4f88190a80316394940627d |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b07d872c81908f912263d8f7c80d |
completed | May 3, 2026, 8:30 p.m. |
Created at: April 9, 2026, 10:11 p.m.