Triple
T20005938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Child of Deaf Adults |
E494460
|
entity |
| Predicate | filmCODAType |
P9709
|
FINISHED |
| Object | feature film about a hearing child of deaf adults |
—
|
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: feature film about a hearing child of deaf adults | Statement: [Child of Deaf Adults, filmCODAType, feature film about a hearing child of deaf adults]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmCODAType Context triple: [Child of Deaf Adults, filmCODAType, feature film about a hearing child of deaf adults]
-
A.
filmTypeContext
Indicates the contextual relationship between a film and its type or category within a specific classification or usage setting.
-
B.
filmType
chosen
Indicates the specific category or genre that a film belongs to.
-
C.
filmGenreOfRelatedWork
Indicates that a work is related to another work through sharing or being associated with the same film genre.
-
D.
distributedFilmType
Indicates that a film was distributed in a particular format or category of distribution.
-
E.
filmBase
Indicates the primary location or headquarters from which a film-related entity (such as a production, company, or operation) is based or operates.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a57ef881909115c8aa232b1012 |
completed | April 20, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:33 p.m.