Triple
T3156449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wendi Deng |
E65995
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Star TV |
E86241
|
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: Star TV | Statement: [Wendi Deng, employer, Star TV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Star TV Context triple: [Wendi Deng, employer, Star TV]
-
A.
Star TV
chosen
Star TV is a major Asian satellite television network known for its broad entertainment and news programming across multiple countries.
-
B.
TVS Television Network
TVS Television Network was an American syndicated sports television network known for broadcasting a wide range of live sporting events and special programming from the 1960s through the 1980s.
-
C.
Ora TV
Ora TV is a digital television network and production company co-founded by Larry King that creates and distributes original online video programming.
-
D.
ThisTV Network
ThisTV Network is a U.S. digital multicast television network known for airing a wide selection of classic movies and television series.
-
E.
Start TV
Start TV is an American digital broadcast television network that primarily airs classic, female-led procedural dramas from the 1980s through the early 2000s.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5eafa4c8190a65cc1312823144c |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b225068444819080e2b8b6b1260613 |
completed | March 12, 2026, 2:29 a.m. |
Created at: March 8, 2026, 3:05 p.m.