Triple
T18354693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Foreign Affair |
E439757
|
entity |
| Predicate | starredRole |
P1668
|
FINISHED |
| Object | Marlene Dietrich as a glamorous cabaret singer |
—
|
LITERAL 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: Marlene Dietrich as a glamorous cabaret singer | Statement: [A Foreign Affair, starredRole, Marlene Dietrich as a glamorous cabaret singer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starredRole Context triple: [A Foreign Affair, starredRole, Marlene Dietrich as a glamorous cabaret singer]
-
A.
starredActor
Indicates that an actor performed a leading or significant role in a particular production or work.
-
B.
actorRole
Indicates that an entity participates in an event or action in a specific capacity or function (such as performer, initiator, or responsible party).
-
C.
replacesInLeadRole
Indicates that one entity takes over or substitutes for another entity in the primary or leading role within a given context or production.
-
D.
isPrimaryStarOf
Indicates that a star serves as the main or central stellar object in relation to a specified system, object, or context.
-
E.
playedRoleIn
chosen
Indicates that an entity performed or assumed a specific role or character within a particular event, production, or context.
- F. None of above.
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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d458148190849ed28fa90eb92b |
completed | April 19, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e44fed3fdc81908f4ed6a81db42416 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.