Triple
T35728109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo! |
E1032670
|
entity |
| Predicate | screenwriterOfSegmentMerde |
P182473
|
FINISHED |
| Object | Leos Carax |
—
|
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: Leos Carax | Statement: [Tokyo!, screenwriterOfSegmentMerde, Leos Carax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenwriterOfSegmentMerde Context triple: [Tokyo!, screenwriterOfSegmentMerde, Leos Carax]
-
A.
screenwriterOfWork
Indicates that a person served as the screenwriter (wrote the screenplay) for a particular creative work.
-
B.
screenwriterOfContainingFilm
chosen
Indicates that one entity is the screenwriter who wrote the screenplay for a film in which the other entity is contained (e.g., as a segment, episode, or part).
-
C.
screenwriterOfWorkCreator
Indicates that one entity is the screenwriter who created or wrote the screenplay for a particular work.
-
D.
screenwriterOfDepiction
Indicates that one entity is the screenwriter responsible for the script of a particular depiction or representation of a work or subject.
-
E.
screenwriterOfWorkAppearingIn
Indicates that a person is the screenwriter of a work in which a specified entity (such as a character, actor, or role) appears.
- 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_69f76e102b5881909e5d63a30a5cecbe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:05 p.m.