Triple
T32494932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breathless (1983 film) |
E830492
|
entity |
| Predicate | studentCharacterFieldOfStudy |
P123410
|
FINISHED |
| Object | architecture |
—
|
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: architecture | Statement: [Breathless (1983 film), studentCharacterFieldOfStudy, architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studentCharacterFieldOfStudy Context triple: [Breathless (1983 film), studentCharacterFieldOfStudy, architecture]
-
A.
characterFieldOfStudy
chosen
Indicates the academic or disciplinary field that a character studies or specializes in.
-
B.
offersFieldOfStudy
Indicates that an institution or program provides a particular field of study as an available area of academic focus.
-
C.
studiedUnder
Indicates that one entity received instruction, training, or mentorship from another, typically in an academic or apprenticeship context.
-
D.
studiesIn
Indicates that a person is enrolled as a student at, and pursues their studies within, a particular educational institution or program.
-
E.
hasSubjectOfStudy
Indicates that an entity (such as a person or organization) focuses on, researches, or specializes in a particular field or topic of study.
- 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_69f34920aa4081908d8fb0277414b911 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 12:59 a.m.