Triple
T16170780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Milch |
E392427
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Home Box Office |
E101308
|
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: Home Box Office | Statement: [David Milch, employer, Home Box Office]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Home Box Office Context triple: [David Milch, employer, Home Box Office]
-
A.
Home Box Office
chosen
Home Box Office is a premium American cable and streaming television network best known for its high-quality original series, films, and specials.
-
B.
Sky Box Office
Sky Box Office is a pay-per-view television service from Sky that offers subscribers access to premium movies, sports events, and special programming.
-
C.
Mr. Box Office
Mr. Box Office is an American sitcom about a famous movie star sentenced to teach at an inner-city high school, blending celebrity culture with classroom comedy.
-
D.
Blockbusters
Blockbusters is a British television quiz show, originally popular in the 1980s, in which contestants answer general knowledge questions to complete a path across a hexagonal game board.
-
E.
At the Movies
At the Movies was a long-running American film review television program, best known for featuring critics like Roger Ebert who popularized the "thumbs up/thumbs down" style of movie criticism.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21eb6de30819083af54b50ae5ae51 |
completed | April 17, 2026, 11:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff7bd87f08190a9f2a1524e5db2ba |
completed | May 10, 2026, 3:13 a.m. |
Created at: April 10, 2026, 5:02 a.m.