Triple
T35469334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jewel Staite as Kaylee Frye |
E1025164
|
entity |
| Predicate | portrayalDebutWork |
P92133
|
FINISHED |
| Object | Firefly episode “Serenity” |
—
|
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: Firefly episode “Serenity” | Statement: [Jewel Staite as Kaylee Frye, portrayalDebutWork, Firefly episode “Serenity”]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayalDebutWork Context triple: [Jewel Staite as Kaylee Frye, portrayalDebutWork, Firefly episode “Serenity”]
-
A.
debutWork
Indicates the work (such as a book, film, album, or performance) that marks an entity’s first public or professional appearance in a given field.
-
B.
portrayedInWork
Indicates that an entity is depicted or represented as a character, figure, or subject within a specific creative work.
-
C.
debutTitleOf
Indicates that one entity is the first work (e.g., book, album, film) with which another entity made its debut.
-
D.
portrayedByWork
Indicates that a work (such as a film, book, or artwork) depicts, represents, or portrays a particular entity.
-
E.
portraysInWork
chosen
Indicates that one entity depicts, represents, or plays the role of another entity within a specific creative work.
- 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_69f76dfa20d0819089585dc2cf653aea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff4de66ba481908e7184b3cf9d4d2d |
completed | May 9, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69ff4c702a5881909c6684c74807e945 |
completed | May 9, 2026, 3:02 p.m. |
Created at: May 3, 2026, 4:04 p.m.