Triple
T17977658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Branch |
E449517
|
entity |
| Predicate | roleInTrolls (2016 film) |
P120050
|
FINISHED |
| Object | deuteragonist |
—
|
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: deuteragonist | Statement: [Branch, roleInTrolls (2016 film), deuteragonist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInTrolls (2016 film) Context triple: [Branch, roleInTrolls (2016 film), deuteragonist]
-
A.
التأثير
Indicates a relationship where one entity produces a change or has an influence on another entity or its state.
-
B.
როლები
chosen
Indicates that an entity has specific roles, functions, or positions assigned or associated with it in a given context.
-
C.
سبب التسمية
Indicates the reason or cause behind assigning a particular name to something.
-
D.
له طابع
Indicates that something possesses or exhibits a particular character, style, or distinctive quality.
-
E.
roleInFilmEcosystem
Indicates the specific function or position an entity holds within the broader network of activities, stakeholders, and processes that make up the film ecosystem.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b200e9108190bcdde5ba7938ba94 |
completed | April 19, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:22 a.m.