Triple
T5043360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shotgun |
E113598
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Sterling Hayden |
E20817
|
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: Sterling Hayden | Statement: [Shotgun, leadActor, Sterling Hayden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sterling Hayden Context triple: [Shotgun, leadActor, Sterling Hayden]
-
A.
Sterling Hayden
chosen
Sterling Hayden was an American actor and World War II hero known for his rugged film roles and his clandestine service as a Marine and OSS operative.
-
B.
Eddie Bracken
Eddie Bracken was an American comedic actor known for his roles in 1940s and 1950s film comedies and Broadway productions.
-
C.
Richard Basehart
Richard Basehart was an American actor known for his versatile film and television roles, including performances in "La Strada" and the TV series "Voyage to the Bottom of the Sea."
-
D.
Zachary Scott
Zachary Scott was an American actor best known for his suave yet often villainous roles in 1940s and 1950s Hollywood films.
-
E.
Edmond O'Brien
Edmond O'Brien was an American character actor and Academy Award winner known for his intense, hard-boiled performances in film noir and classic Hollywood dramas.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fc04f08190aba851fa0192d0fb |
completed | March 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bffc1b472c819087590fe2b8713ded |
completed | March 22, 2026, 2:26 p.m. |
Created at: March 20, 2026, 1:37 p.m.