Triple
T34251918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middle-earth Enterprises |
E878770
|
entity |
| Predicate | controlsFilmRightsFor |
P6247
|
FINISHED |
| Object | The Lord of the Rings |
—
|
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: The Lord of the Rings | Statement: [Middle-earth Enterprises, controlsFilmRightsFor, The Lord of the Rings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlsFilmRightsFor Context triple: [Middle-earth Enterprises, controlsFilmRightsFor, The Lord of the Rings]
-
A.
ownedByInFilm
Indicates that one entity is portrayed as being owned or possessed by another entity within the context of a specific film.
-
B.
mediaRightsValue
Indicates the monetary worth or valuation assigned to the rights to use, distribute, or exploit a piece of media.
-
C.
mediaRights
chosen
Indicates that one entity holds legal permission or authority to use, distribute, or control the use of another entity’s media content.
-
D.
hasTypeOfUseInFilm
Indicates that something is associated with a specific manner or category of use within the context of a film.
-
E.
appliesToFilm
Indicates that something (such as a rule, feature, attribute, or condition) is relevant or applicable to a particular film.
- 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_69f349b3618481909df955b063f305b2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fea5e828cc8190a9b755a645dc56d2 |
completed | May 9, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69fea36443f08190b2aced9b4a0525fd |
completed | May 9, 2026, 3 a.m. |
Created at: May 1, 2026, 1:56 a.m.