Triple
T15059584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Lieutenant |
E379589
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Joe Delia |
E392232
|
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: Joe Delia | Statement: [Bad Lieutenant, musicBy, Joe Delia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Delia Context triple: [Bad Lieutenant, musicBy, Joe Delia]
-
A.
Joe Delia
chosen
Joe Delia is an American composer and musician best known for his film and television scores, particularly his collaborations with director Abel Ferrara.
-
B.
Mel Dinelli
Mel Dinelli was an American playwright and screenwriter best known for his work in film noir and suspense films during the mid-20th century.
-
C.
Day O’Connor
Day O’Connor is the family name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
-
D.
Jo Lupo
Jo Lupo is a tough, highly skilled former U.S. Army Ranger who serves as the no-nonsense deputy sheriff in the quirky, science-driven town of Eureka on the TV series "Eureka."
-
E.
Dannie McElroy
Dannie McElroy is a character in Patricia Highsmith’s novel "The Price of Salt" (also known as "Carol"), known primarily as a close friend and confidant of Therese Belivet.
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee50afc8190bf7b0f4bbe8c60a3 |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5c2fcec8190800d1bda82c7352e |
completed | May 9, 2026, 3:10 a.m. |
Created at: April 10, 2026, 3:01 a.m.