Triple
T2308172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raging Bull |
E51889
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Mardik Martin |
E243087
|
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: Mardik Martin | Statement: [Raging Bull, screenwriter, Mardik Martin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mardik Martin Context triple: [Raging Bull, screenwriter, Mardik Martin]
-
A.
Mardik Martin
chosen
Mardik Martin was an American screenwriter best known for his long-time collaboration with director Martin Scorsese on films such as "Mean Streets" and "Raging Bull."
-
B.
Roderic Dallas
Roderic Dallas was a distinguished Australian fighter ace of World War I who became one of the leading pilots in British naval aviation.
-
C.
Michele Lamar Richards
Michele Lamar Richards is an American actress best known for her supporting role in the 1992 romantic thriller film "The Bodyguard."
-
D.
Jerry Dandrige
Jerry Dandrige is the charismatic yet sinister vampire antagonist in the 2011 horror-comedy film "Fright Night."
-
E.
Victor Milner
Victor Milner was an American cinematographer and Academy Award winner known for his work on numerous classic Hollywood films during the early to mid-20th century.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc605cf808190a326e6c78e3f9166 |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae7f379bbc8190b085b82e2e16401e |
completed | March 9, 2026, 8:05 a.m. |
Created at: March 4, 2026, 7:49 p.m.