Triple
T15419309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ben Stiller as David Starsky |
E369330
|
entity |
| Predicate | partOfOnScreenDuo |
P46169
|
FINISHED |
| Object | Starsky and Hutch |
E75413
|
NE FINISHED |
How this triple was built (3 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: Starsky and Hutch | Statement: [Ben Stiller as David Starsky, partOfOnScreenDuo, Starsky and Hutch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Starsky and Hutch Context triple: [Ben Stiller as David Starsky, partOfOnScreenDuo, Starsky and Hutch]
-
A.
Starsky & Hutch
chosen
Starsky & Hutch is a 2004 action-comedy film adaptation of the 1970s TV series, starring Ben Stiller and Owen Wilson as mismatched detectives in a stylized, humorous take on buddy-cop crime fighting.
-
B.
Dragnet
Dragnet is a 1987 comedy crime film that parodies the classic police procedural TV series, starring Dan Aykroyd and Tom Hanks as mismatched Los Angeles detectives.
-
C.
Third Watch
Third Watch is an American television drama series that follows the lives of New York City police officers, firefighters, and paramedics working the 3 p.m. to 11 p.m. shift.
-
D.
Mannix
Mannix is an American television detective series from the late 1960s and 1970s, centered on the tough, resourceful private investigator Joe Mannix.
-
E.
T.J. Hooker (TV series)
T.J. Hooker is an American police drama television series from the 1980s starring William Shatner as a veteran cop training new recruits.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfOnScreenDuo Context triple: [Ben Stiller as David Starsky, partOfOnScreenDuo, Starsky and Hutch]
-
A.
hasOnscreenPartner
Indicates that one entity appears together with another as a partner within the same onscreen context or scene.
-
B.
bodyPartDisplayed
Indicates that a specific body part of an entity is being visibly shown or exposed in a given context.
-
C.
isPartiallyVisibleFrom
Indicates that one entity can be seen only in part, rather than fully, from the viewpoint or location of another entity.
-
D.
screensAt
Indicates that one entity shows, projects, or displays another entity (such as a film, program, or content) on a screen or at a screening venue.
-
E.
associatedWithDuo
chosen
Indicates a relationship in which an entity is linked or connected to a specific duo, typically implying involvement, collaboration, or relevance to that pair.
- F. None of above.
Provenance (4 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ebce4f48190ba282ecb4fb2f6fa |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb593258081909dcaf2b37fd28e63 |
completed | May 9, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69ded27f45548190a6d2b1b85cb47444 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:20 a.m.