Triple
T15390585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | America Ferrera |
E368032
|
entity |
| Predicate | characterPortrayed |
P1507
|
FINISHED |
| Object | Astrid Hofferson |
E388741
|
NE 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: Astrid Hofferson | Statement: [America Ferrera, characterPortrayed, Astrid Hofferson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Astrid Hofferson Context triple: [America Ferrera, characterPortrayed, Astrid Hofferson]
-
A.
Astrid Hofferson
chosen
Astrid Hofferson is a brave and skilled Viking warrior and dragon rider from the "How to Train Your Dragon" franchise, known as Hiccup's close friend and eventual love interest.
-
B.
Willa Hoffman
Willa Hoffman is the daughter of costume designer and director Mimi O'Donnell and the late actor Philip Seymour Hoffman.
-
C.
Annette Stroyberg
Annette Stroyberg was a Danish actress and model best known for her roles in European films of the late 1950s and 1960s.
-
D.
Elizabeth Hofmann
Elizabeth Hofmann is known as the spouse of American glass artist and sculptor Dan Dailey.
-
E.
Judy Hofflund
Judy Hofflund is a film producer known for her work on major studio projects, including the 2022 adaptation of "Death on the Nile."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e7727a081908eff45bbc1633c8a |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff9085d388819092be2fd8a0268e23 |
completed | May 9, 2026, 7:52 p.m. |
Created at: April 10, 2026, 3:19 a.m.