Triple
T20711645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Love a Cop |
E509061
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | I Love a Cop |
—
|
NE NERFINISHED |
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: I Love a Cop | Statement: [I Love a Cop, hasTitle, I Love a Cop]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: I Love a Cop Context triple: [I Love a Cop, hasTitle, I Love a Cop]
-
A.
"I Love a Cop"
chosen
"I Love a Cop" is a song from the 1959 Broadway musical *Fiorello!*, which portrays the personal and political life of New York mayor Fiorello H. La Guardia.
-
B.
The Cop in Blue Jeans
The Cop in Blue Jeans is a 1976 Italian crime-comedy film starring Tomas Milian as an unorthodox Roman police inspector battling street crime.
-
C.
One Good Cop
One Good Cop is a 1991 crime drama film starring Michael Keaton as a New York City detective who must balance his dangerous job with caring for his late partner’s three young daughters.
-
D.
Cops
Cops is a long-running American reality television series that follows police officers on duty as they respond to real-life incidents and arrests.
-
E.
Hollywood Cop
Hollywood Cop is a 1987 action-comedy film about a tough Los Angeles detective who teams up with a rookie to protect a woman and her son from violent criminals.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1cdcaac8190b9ba82d489fb3bfc |
completed | April 21, 2026, 12:16 a.m. |
Created at: April 16, 2026, 12:15 p.m.