Triple
T23898404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Close Enough (2017 short film) |
E600969
|
entity |
| Predicate | featuresDeafPerformer |
P101716
|
FINISHED |
| Object | Millicent Simmonds |
—
|
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: Millicent Simmonds | Statement: [Close Enough (2017 short film), featuresDeafPerformer, Millicent Simmonds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresDeafPerformer Context triple: [Close Enough (2017 short film), featuresDeafPerformer, Millicent Simmonds]
-
A.
featuresPerformerType
chosen
Indicates that something includes or highlights a performer of a specified type (e.g., musician, actor, or other performance role).
-
B.
featuresMusician
Indicates that something (such as a work, event, or recording) prominently includes or showcases a particular musician.
-
C.
featuresOnScreenPerformer
Indicates that something (such as a work or production) includes a particular performer visibly appearing on screen.
-
D.
featuresPerformerCameo
Indicates that the subject includes a brief, special appearance by a performer who is not part of the main cast or lineup.
-
E.
coPerformer
Indicates that two or more entities jointly perform the same act or participate together in the same performance.
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cddb3fdc819096dc84a1774d9bee |
completed | April 29, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:25 p.m.