Triple
T22675600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 90th Academy Awards ceremony |
E560336
|
entity |
| Predicate | bestSupportingActressFilm |
P8120
|
FINISHED |
| Object | I, Tonya |
—
|
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: I, Tonya | Statement: [90th Academy Awards ceremony, bestSupportingActressFilm, I, Tonya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: I, Tonya Context triple: [90th Academy Awards ceremony, bestSupportingActressFilm, I, Tonya]
-
A.
I, Tonya
chosen
I, Tonya is a 2017 biographical dark comedy-drama film about figure skater Tonya Harding and the scandal surrounding the attack on Nancy Kerrigan.
-
B.
Tonya
Tonya is a feminine given name most famously associated with former American figure skater Tonya Harding.
-
C.
Tonya
Tonya is a character from the film "Doctor Zhivago," known as Yuri Zhivago’s devoted wife whose relationship contrasts with his passionate affair with Lara.
-
D.
Tonya
Tonya is a central female character in August Wilson’s play "King Hedley II," known for her poignant struggle over motherhood, survival, and hope in 1980s Pittsburgh.
-
E.
Tonya
Tonya is the mischievous and often troublemaking younger sister of Chris in the sitcom "Everybody Hates Chris."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17823bd1881908958b0a8ba59e199 |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:11 p.m.