Triple
T32876068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tabu: A Story of the South Seas |
E840930
|
entity |
| Predicate | finalFilmOf |
P87468
|
FINISHED |
| Object | F. W. Murnau |
—
|
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: F. W. Murnau | Statement: [Tabu: A Story of the South Seas, finalFilmOf, F. W. Murnau]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalFilmOf Context triple: [Tabu: A Story of the South Seas, finalFilmOf, F. W. Murnau]
-
A.
finalFilmBy
chosen
Indicates that a given film is the last movie directed, produced, or otherwise primarily created by a particular person or entity in their career or filmography.
-
B.
finalAct
Indicates that an action or event is the last or concluding act in a sequence or process.
-
C.
finalFilmPerformanceOf
Indicates that one entity is the last film performance or role undertaken by the other entity before they stopped acting in films.
-
D.
endedWithFilm
Indicates that an event, series, or process concluded with the showing, release, or occurrence of a particular film.
-
E.
finalOperaOf
Indicates that one entity is the last opera composed by another entity.
- 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_69f349436ee88190b72ee12d0f3f508e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fdf5d05cc481909ec9e1b1f0784279 |
completed | May 8, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69fdf0cdd6948190838864ab3120dfa6 |
completed | May 8, 2026, 2:18 p.m. |
Created at: May 1, 2026, 1:18 a.m.