Triple
T822028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steven S. DeKnight |
E17769
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Starz |
E88556
|
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: Starz | Statement: [Steven S. DeKnight, employer, Starz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Starz Context triple: [Steven S. DeKnight, employer, Starz]
-
A.
Starz Entertainment
chosen
Starz Entertainment is an American premium cable and streaming media company known for producing and distributing original television series and films.
-
B.
The Weinstein Company
The Weinstein Company was an American independent film studio and distributor founded by Bob and Harvey Weinstein, known for producing and releasing numerous critically acclaimed and award-winning films.
-
C.
Lionsgate
Lionsgate is a major North American entertainment company and film studio known for producing and distributing a wide range of popular movies and television series.
-
D.
Entertainment One
Entertainment One is a multinational entertainment company known for producing and distributing films, television programming, and other media content worldwide.
-
E.
Showtime
Showtime is an American premium cable and streaming network known for its original, often edgy series, films, and sports 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_69a4937bcaac8190a322524ac6f45a5a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab7c139c8190b6d75661b5138d89 |
completed | March 1, 2026, 9:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d91c2948190bc13a223548facba |
completed | March 3, 2026, 11:24 p.m. |
Created at: March 1, 2026, 7:38 p.m.