Triple
T26635108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Kelly |
E668612
|
entity |
| Predicate | starGloriaSwansonLaterAppearedIn |
P161076
|
FINISHED |
| Object | Sunset Boulevard |
—
|
NE NERFINISHED |
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: Sunset Boulevard | Statement: [Queen Kelly, starGloriaSwansonLaterAppearedIn, Sunset Boulevard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starGloriaSwansonLaterAppearedIn Context triple: [Queen Kelly, starGloriaSwansonLaterAppearedIn, Sunset Boulevard]
-
A.
hasGingerRogersRole
Indicates that an entity is assigned or associated with a role specifically identified as the "Ginger Rogers" role in a given context or production.
-
B.
hasMarleneDietrichRoleType
Indicates that an entity has a specific type or category of role associated with Marlene Dietrich.
-
C.
MarilynMonroeRoleType
Indicates the type or category of role associated with Marilyn Monroe in a given context.
-
D.
MarilynMonroeRole
Indicates that the subject entity has (or had) a role or character portrayed by Marilyn Monroe.
-
E.
hasElizabethTaylorRole
Indicates that an entity has a role that was originally played by, associated with, or famously portrayed by Elizabeth Taylor.
- F. None of above. chosen
Provenance (4 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_69ee9d0024b8819090a7c8cf669a3b6c |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f616298eb48190913aefb29005cd67 |
completed | May 2, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
| PDg | Predicate description generation | batch_69f60f24ed608190bffe6c6084fc2f7a |
completed | May 2, 2026, 2:50 p.m. |
Created at: April 27, 2026, 2:26 a.m.