Triple
T26729700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Actress for Resurrection |
E673933
|
entity |
| Predicate | forPerformanceBy |
P161175
|
FINISHED |
| Object | Ellen Burstyn |
—
|
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: Ellen Burstyn | Statement: [Academy Award for Best Actress for Resurrection, forPerformanceBy, Ellen Burstyn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forPerformanceBy Context triple: [Academy Award for Best Actress for Resurrection, forPerformanceBy, Ellen Burstyn]
-
A.
intendedForPerformanceBy
Indicates that something (such as a work, role, or piece) is designed or meant to be performed by a particular performer or type of performer.
-
B.
originalPerformanceFor
Indicates that one entity is the original performance or execution from which another related version, recording, or representation is derived.
-
C.
supportingPerformanceBy
Indicates that one performance serves as a supporting or secondary act that complements or enhances another primary performance.
-
D.
performedTo
Indicates that an action or performance is directed toward or carried out on a particular entity.
-
E.
performanceWith
Indicates a relationship where two or more entities participate together in the same performance or staged presentation.
- 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_69eecda57ab481909424e98f2835e7d8 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f618401d2481908b10199b30333192 |
completed | May 2, 2026, 3:29 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
| PDg | Predicate description generation | batch_69f6106d346c8190868489f36c65b6ec |
completed | May 2, 2026, 2:55 p.m. |
Created at: April 27, 2026, 3:44 a.m.