Triple
T2326682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Curtiz |
E48302
|
entity |
| Predicate | numberOfFilmsDirected |
P38922
|
FINISHED |
| Object | over 100 |
—
|
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: over 100 | Statement: [Michael Curtiz, numberOfFilmsDirected, over 100]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfFilmsDirected Context triple: [Michael Curtiz, numberOfFilmsDirected, over 100]
-
A.
numberOfDirectors
Indicates the total count of directors associated with a given entity.
-
B.
numberOfFilmsAppearedIn
Indicates the total count of distinct films in which a given entity has appeared.
-
C.
directorSince
Indicates that one entity has held the role of director for another entity starting from a specified point in time.
-
D.
numberOfAcademyAwardsForBestDirector
Indicates the total count of Academy Awards received by a director for the Best Director category.
-
E.
producedFilm
Indicates that one entity served as the producer (or production company) responsible for making or financing the creation of a particular film.
- F. None of above. chosen
Provenance (4 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abcc30c5e881908c5d526d7e7491d0 |
completed | March 7, 2026, 6:56 a.m. |
| PD | Predicate disambiguation | batch_69abc5926d048190a535e3f23d41de2a |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcc2fa25c8190858c1c541b914f4c |
completed | March 7, 2026, 6:56 a.m. |
Created at: March 4, 2026, 7:50 p.m.