Triple
T3202003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Last Tycoon |
E67071
|
entity |
| Predicate | starred |
P5563
|
FINISHED |
| Object | Dana Andrews |
E391255
|
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: Dana Andrews | Statement: [The Last Tycoon, starred, Dana Andrews]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dana Andrews Context triple: [The Last Tycoon, starred, Dana Andrews]
-
A.
Dana Andrews
chosen
Dana Andrews was a prominent American film actor of the 1940s and 1950s, best known for his leading roles in classics such as "Laura" and "The Best Years of Our Lives."
-
B.
Robert Cummings
Robert Cummings was an American film and television actor best known for his roles in comedies and thrillers during Hollywood’s Golden Age.
-
C.
William Holden
William Holden was an acclaimed American film actor known for his charismatic performances in classics such as "Sunset Boulevard," "Stalag 17," and "The Bridge on the River Kwai."
-
D.
Glenn Ford
Glenn Ford was a Canadian-American film actor renowned for his versatile performances in classic Hollywood movies such as "Gilda," "The Big Heat," and "Blackboard Jungle."
-
E.
Victor Mature
Victor Mature was an American film actor known for his rugged leading-man roles in 1940s and 1950s Hollywood epics and adventure films.
- 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_69ad8589bd988190afa7ed2bdffb7b33 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada9b046c8819087c0a61c4f9adeb7 |
completed | March 8, 2026, 4:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a81796fc8190b96e1feff3a73cba |
completed | March 14, 2026, 6:25 p.m. |
Created at: March 8, 2026, 3:07 p.m.